Server definition
- Hash
- sha256:c67856c3089fae3e713422000b8b56eb4acdb3590f9874ec24af9fab9222968c
- What it is
- What a remote MCP server returned when asked what it offers: 51 tools
The blob, as servednamed by its sha256
{
"instructions": "GoldSeam is the marketplace for teaching, training and learning: one endpoint where you explore what postsecondary organizations offer, compare what actually differs between them, and help a person engage with the organization that decides. Every answer names the contract that produced it and the snapshot it was read from, and an absence is stated rather than filled in. CourseShelf — colleges and what they teach, from the institutions' own published catalogs: a school, its programs, its courses, its checklists (the requirements for an award), its catalogs and its published policies. GoldCheck — will my credits transfer: a course already taken, or an exam score, read against a named school's own published rules. GoldRibbon — a person's own record: their documents and experiences, their Competency Selfie, and what their prior learning may earn against a named program's checklist. The agent keeps the package; GoldSeam stores nothing. Industry Certifications — search by a trade, field, job or company: what a certification requires, the occupations it serves, and who issues it. Transitions — where a path can lead: the destinations reachable from an occupation, and how they compare. KSA Dictionary — the shared vocabulary: where a word places in the KSA model, so a learner's words and a learning offering's words resolve to the same identifiers. GoldChoice — helps a person choose what to study, where, and how to get there: majors compared, schools matched to what matters to you, and what your prior learning is already worth. When a person connects, or asks what this is: introduce GoldSeam, name what it can answer, and offer two or three of the example questions in the `goldseam://start` resource — do not wait to be asked. For a person's plain question about a certification, start with search_certifications using their key words: a trade, field, job, or company ('nursing', 'HVAC', 'IBM'). Ids and codes come from earlier answers: pass a result's id to get_certification, occupations_for_certification, or related_certifications; when the person has an occupation code (SOC, e.g. 29-1141) use certifications_for_occupation, and for a college program code (CIP, e.g. 51.3801) use certifications_for_program; list_issuers names the issuing organizations. For what a word means in the KSA model use resolve_term or expand_term; to cross a program code to occupations or back use crosswalk_code; get_dictionary_summary says what the dictionary itself holds (its words, meanings, governed terms, elements and link words), so never answer that from memory. An answer marked not_held is an honest absence — say so rather than filling the gap from memory. CourseShelf answers from the published college catalogs, one family of services per object of its model. find_institution takes a name or IPEDS UNITID ('Grayson', '225070'), or a state ('WY') for that state's institutions, or nothing for the states themselves; get_institution returns everything held about one. With a UNITID: programs_for_institution, learning_units (its courses), find_checklists, find_catalogs and find_policies; find_programs searches programs across institutions. With an id from those answers: get_program, get_checklist (a checklist is the generic itinerary of requirements for an award), get_learning_unit, get_catalog and get_policy; checklists_requiring_learning_unit lists the checklists that require a course; search_programs_and_learning_units finds programs and courses as product cards with counts to refine by (courses across every school need words of 3 or more characters); present its answer the way the portal shop does: the cards first (name, award, school and city, subject, credits), then the top refinements with their counts, then offer See checklist from each card's next_actions; for a program question show programs before certifications, and offer portal_url to see the same view; get_courseshelf_summary says what CourseShelf holds (institutions with loaded content per area, table counts, the census), as published; compare_program_checklists sets several institutions' checklists for a program beside their published costs. Agreements, pathways, course comparability (published transfer rules) and transfer frameworks: find_agreements and get_agreement, find_pathways and get_pathway, find_comparability and get_comparability, find_transfer_frameworks and get_transfer_framework — each answers none held when the build holds none. comparability_for_learning_unit answers a course's published transfer rules, where it lands and what lands on it (exams included): the rules CourseShelf holds first, then CourseAtlas's direct rules read live; say each rule as the school's own statement, comparable and never equivalent, with its source. Certifications are answered by the certification tools. Every CourseShelf answer states its census_reading and census_cleared; when census_cleared is false the catalog figures are still being captured, so state their status: not yet census-cleared. A linked record that did not resolve is stated unresolved, never guessed. Where an occupation can lead: find_transitions takes a SOC code (from_soc, e.g. 51-4121) and answers destination occupations, each with its typed roads (published: O*NET related occupations or a credential serving both; mapped: a CIP the crosswalk joins them through), each road with its class's karat (published 24k, mapped 18k), the bridges (credentials with their conditions, and CourseShelf programs whose CIP maps there, in the state given), and demand as O*NET publishes it; compare_destinations lines 2 to 6 destinations up side by side. These are roads, not a person's fit: whether a person is ready is GoldCheck's, never inferred from the roads. GoldRibbon helps a person show what they have learned, and keeps nothing: you hold their package. Ask for their documents and experiences, then:\n1. `assemble_my_formal_education` (transcripts), `assemble_my_work_and_credentials` (resume, LinkedIn, certifications, military, apprenticeship) and `assert_my_life_experiences` (their own statements), in any order, passing the package each returns into the next call.\n2. `my_selfie_ksa_view` makes their Selfie from the package. Offer them their unresolved items to place or dismiss, and pass their answers back in the package.\n3. When they name a school: `will_my_credits_transfer` with the `held` items formal education returned. Then `draft_my_claims` (give it the school) drafts what their other learning shows; let them keep, affirm or decline each claim in the package.\n4. Ask which program they are aiming for, and find it with `find_programs` at that school. Then `suggest_credit_for_my_learning`, giving that program's checklist_id: the answer is that program line by line, each line may be met, already covered or still needed, and learning no line matches stands as block credit. Without a program no course is suggested, only block credit.\nRecognition is always the school's decision: say \"may\", never \"will\". Keep the package for them; it is theirs to keep or share.",
"tools": [
{
"description": "Read a person's transcripts into their evidence package: each file's text and status, its courses and exams as rows, and the items will_my_credits_transfer takes (courses as { unitid or school, code }; AP, CLEP and IB exams with a score). Ask the person for each transcript and the school it came from. Several transcripts are read side by side. A school several schools' names fit is answered with the candidates, and nothing is read. Nothing is stored: the answer returns the package for the agent to keep.",
"inputSchema": {
"properties": {
"files": {
"description": "1 or more transcripts",
"items": {
"properties": {
"content_base64": {
"description": "The file's bytes, base64. A call's files total at most about 1.5 MB; send more over several calls with the same package.",
"type": "string"
},
"filename": {
"type": "string"
},
"school": {
"description": "The school the transcript came from, a name or initials (e.g. CNM); ask the person",
"type": "string"
},
"slot": {
"enum": [
"transcript"
],
"type": "string"
},
"unitid": {
"description": "Or the school's IPEDS UNITID, e.g. 187532",
"type": "string"
}
},
"required": [
"slot",
"filename",
"content_base64"
],
"type": "object"
},
"type": "array"
},
"package": {
"description": "The goldribbon_package_v1 object an earlier GoldRibbon answer returned. Keep it for the person and send it back whole; GoldSeam keeps no copy.",
"type": "object"
}
},
"required": [
"files"
],
"type": "object"
},
"name": "assemble_my_formal_education",
"outputSchema": {
"properties": {
"candidates": {
"description": "When several schools fit a name: each file's candidates",
"type": "array"
},
"contract": {
"type": "string"
},
"counts": {
"description": "files, readable, courses, exams",
"type": "object"
},
"files": {
"description": "Each file read, with its extraction_status",
"type": "array"
},
"limits": {
"description": "What this answer could not do, each { code, statement }",
"type": "array"
},
"next_actions": {
"items": {
"properties": {
"arguments": {
"type": "object"
},
"label": {
"type": "string"
},
"tool": {
"description": "A GoldSeam service",
"type": "string"
}
},
"required": [
"label",
"tool",
"arguments"
],
"type": "object"
},
"type": "array"
},
"package": {
"description": "The person's package, with this service's part filled",
"type": "object"
},
"statement": {
"type": "string"
}
},
"required": [
"contract",
"statement"
],
"type": "object"
}
},
{
"description": "Read a person's resume, LinkedIn export, certificates, military records and apprenticeship records into their evidence package: each file's text and status, and the credential signals the certificate, military and apprenticeship documents carry. Ask the person for each file. This assembles; the Selfie is my_selfie_ksa_view. Nothing is stored: the answer returns the package for the agent to keep.",
"inputSchema": {
"properties": {
"files": {
"description": "1 or more files",
"items": {
"properties": {
"content_base64": {
"description": "The file's bytes, base64. A call's files total at most about 1.5 MB; send more over several calls with the same package.",
"type": "string"
},
"filename": {
"type": "string"
},
"slot": {
"enum": [
"resume",
"linkedin_file",
"certs",
"military",
"apprentice"
],
"type": "string"
}
},
"required": [
"slot",
"filename",
"content_base64"
],
"type": "object"
},
"type": "array"
},
"linkedin_url": {
"description": "Optional: the person's LinkedIn profile address",
"type": "string"
},
"package": {
"description": "The goldribbon_package_v1 object an earlier GoldRibbon answer returned. Keep it for the person and send it back whole; GoldSeam keeps no copy.",
"type": "object"
}
},
"required": [
"files"
],
"type": "object"
},
"name": "assemble_my_work_and_credentials",
"outputSchema": {
"properties": {
"contract": {
"type": "string"
},
"counts": {
"description": "files, readable, per_slot, credential_signals",
"type": "object"
},
"files": {
"description": "Each file read, with its extraction_status",
"type": "array"
},
"limits": {
"description": "What this answer could not do, each { code, statement }",
"type": "array"
},
"next_actions": {
"items": {
"properties": {
"arguments": {
"type": "object"
},
"label": {
"type": "string"
},
"tool": {
"description": "A GoldSeam service",
"type": "string"
}
},
"required": [
"label",
"tool",
"arguments"
],
"type": "object"
},
"type": "array"
},
"package": {
"description": "The person's package, with this service's part filled",
"type": "object"
},
"statement": {
"type": "string"
}
},
"required": [
"contract",
"statement"
],
"type": "object"
}
},
{
"description": "Record what a person says they have done outside school and work (family, clubs, sports, faith, travel, self-taught projects, challenges) in their evidence package, each placed in a Selfie dimension by the KSA classifier or left unresolved, never defaulted. These are the person's own statements, kept apart from formal education. Nothing is stored: the answer returns the package for the agent to keep.",
"inputSchema": {
"properties": {
"entries": {
"description": "1 to 20 life experiences",
"items": {
"properties": {
"activity": {
"description": "What the person did, in their words",
"type": "string"
},
"category": {
"enum": [
"passions",
"sports",
"clubs",
"faith",
"family",
"selftaught",
"travel",
"challenges",
"other"
],
"type": "string"
},
"difficulty": {
"enum": [
"remember",
"understand",
"apply",
"analyze",
"evaluate",
"create"
],
"type": "string"
},
"elaboration": {
"type": "string"
},
"life_period": {
"enum": [
"childhood",
"adolescence",
"emerging_adult",
"early_adult",
"midlife",
"experienced",
"later_life"
],
"type": "string"
},
"weight": {
"enum": [
"occasional",
"regular",
"central"
],
"type": "string"
}
},
"required": [
"category",
"activity"
],
"type": "object"
},
"type": "array"
},
"package": {
"description": "The goldribbon_package_v1 object an earlier GoldRibbon answer returned. Keep it for the person and send it back whole; GoldSeam keeps no copy.",
"type": "object"
}
},
"required": [
"entries"
],
"type": "object"
},
"name": "assert_my_life_experiences",
"outputSchema": {
"properties": {
"contract": {
"type": "string"
},
"counts": {
"description": "entries, added, unresolved",
"type": "object"
},
"entries": {
"description": "Each entry with its dimension, placement, facets and placed_by",
"type": "array"
},
"limits": {
"description": "What this answer could not do, each { code, statement }",
"type": "array"
},
"next_actions": {
"items": {
"properties": {
"arguments": {
"type": "object"
},
"label": {
"type": "string"
},
"tool": {
"description": "A GoldSeam service",
"type": "string"
}
},
"required": [
"label",
"tool",
"arguments"
],
"type": "object"
},
"type": "array"
},
"package": {
"description": "The person's package, with this service's part filled",
"type": "object"
},
"statement": {
"type": "string"
}
},
"required": [
"contract",
"statement"
],
"type": "object"
}
},
{
"description": "What certifications serve this occupation? SOC-keyed lookup (dashed SOC accepted with or without the O*NET .00 suffix).",
"inputSchema": {
"properties": {
"limit": {
"description": "Optional page size (default 20, at most 50)",
"type": "integer"
},
"offset": {
"description": "Optional: the next_offset from a previous answer",
"type": "integer"
},
"soc": {
"description": "An occupation code (SOC), e.g. 29-1141 for Registered Nurses or 47-2111 for Electricians — don't know it? search by the job name instead",
"examples": [
"29-1141",
"47-2111"
],
"type": "string"
}
},
"required": [
"soc"
],
"type": "object"
},
"name": "certifications_for_occupation",
"outputSchema": null
},
{
"description": "Broad academic cross-reference by instructional program (CIP). A deliberately broader, lower-precision question than an occupation lookup — never its peer (contract § 4).",
"inputSchema": {
"properties": {
"cip": {
"description": "A college program code (CIP), e.g. 51.3801 for Registered Nursing or 47.0201 for HVAC technology",
"examples": [
"51.3801",
"47.0201"
],
"type": "string"
},
"limit": {
"description": "Optional page size (default 20, at most 50)",
"type": "integer"
},
"offset": {
"description": "Optional: the next_offset from a previous answer",
"type": "integer"
}
},
"required": [
"cip"
],
"type": "object"
},
"name": "certifications_for_program",
"outputSchema": null
},
{
"description": "Which checklists require this course? Each requirement item that resolved to it, with its checklist id, award and group heading. Items that did not resolve to a course are never guessed into this list. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.",
"inputSchema": {
"properties": {
"learning_unit_id": {
"description": "A learning unit id from learning_units or get_learning_unit",
"examples": [
"LU_course_225070_ENGL1301_20262027"
],
"type": "string"
},
"limit": {
"description": "Optional page size (default 20, at most 100)",
"type": "integer"
},
"offset": {
"description": "Optional: the next_offset from a previous answer",
"type": "integer"
}
},
"required": [
"learning_unit_id"
],
"type": "object"
},
"name": "checklists_requiring_learning_unit",
"outputSchema": null
},
{
"description": "Where does this course land at other schools, and what lands on it (exams included)? The published transfer rules for one course: the rules CourseShelf holds first (a school's own catalog, CourseAtlas), then CourseAtlas's direct rules read live. Each rule names its source authority, source_url and band; comparable, never equivalent. What lands on a course is answered from the held rules only. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.",
"inputSchema": {
"properties": {
"code": {
"description": "The course code as printed, e.g. HIST 201",
"type": "string"
},
"direction": {
"description": "lands_as: where it lands; lands_on: what lands on it; both (default)",
"enum": [
"lands_as",
"lands_on",
"both"
],
"type": "string"
},
"learning_unit_id": {
"description": "The course, by its learning unit id",
"type": "string"
},
"limit": {
"description": "Optional page size per list (default 10, at most 50)",
"type": "integer"
},
"offset": {
"description": "Optional: the offset of the next page",
"type": "integer"
},
"school": {
"description": "Or: the course's school, by name (with code or title)",
"type": "string"
},
"target_unitid": {
"description": "Optional: narrow where it lands to one receiving school (IPEDS UNITID)",
"type": "string"
},
"title": {
"description": "Or: the course title, matched exactly",
"type": "string"
},
"unitid": {
"description": "Or: the course's school, by IPEDS UNITID (with code or title)",
"type": "string"
}
},
"type": "object"
},
"name": "comparability_for_learning_unit",
"outputSchema": null
},
{
"description": "Line up 2 to 6 destination occupations side by side from one occupation: the bridge size (credential only, or the program bridges' awards as published), O*NET demand (median wage, outlook, bright outlook) and the evidence classes of the roads. Each cell is copied or counted, never scored.",
"inputSchema": {
"properties": {
"from_soc": {
"description": "The occupation compared from, e.g. 51-4121",
"examples": [
"51-4121"
],
"type": "string"
},
"to_socs": {
"description": "2 to 6 destination SOC codes, e.g. from find_transitions",
"examples": [
[
"51-4122",
"17-3029"
]
],
"items": {
"type": "string"
},
"type": "array"
}
},
"required": [
"from_soc",
"to_socs"
],
"type": "object"
},
"name": "compare_destinations",
"outputSchema": {
"properties": {
"columns": {
"type": "array"
},
"contract": {
"type": "string"
},
"rows": {
"items": {
"properties": {
"label": {
"type": "string"
},
"values": {
"type": "array"
}
},
"type": "object"
},
"type": "array"
},
"statement": {
"type": "string"
},
"understood": {
"type": "object"
}
},
"required": [
"contract",
"statement"
],
"type": "object"
}
},
{
"description": "How do these majors differ? Two to five majors at one level, side by side: definition, the schools offering it, the jobs and their outlook from O*NET, and earnings at 1 and 5 years with debt — given as the LOWEST-TO-HIGHEST RANGE across the schools that publish them, with the number of schools stated. A range of school figures, never a median computed from them. A six-digit major's earnings come from its four-digit series and every such figure is labelled series-level. Every column is complete, or it says which figure is not published.",
"inputSchema": {
"properties": {
"level": {
"description": "The credential level to compare at, e.g. certificate",
"examples": [
"certificate"
],
"type": "string"
},
"majors": {
"description": "2 to 5 majors, each a major_minor_id (e.g. CIP:51.3801) or a CIP code",
"examples": [
[
"CIP:51.3901",
"CIP:51.3902"
]
],
"items": {
"type": "string"
},
"type": "array"
},
"state": {
"description": "Optional two-letter state, for the school counts",
"type": "string"
}
},
"required": [
"majors",
"level"
],
"type": "object"
},
"name": "compare_my_major",
"outputSchema": {
"properties": {
"columns": {
"description": "One column per major, aligned so a gap is never read as a low number",
"items": {
"type": "object"
},
"type": "array"
},
"comparison_rule": {
"type": "string"
},
"contract": {
"type": "string"
},
"not_held": {
"items": {
"type": "object"
},
"type": "array"
},
"statement": {
"type": "string"
},
"understood": {
"type": "object"
}
},
"required": [
"contract",
"statement"
],
"type": "object"
}
},
{
"description": "Which of these schools is better for me? Two to five schools, one major and a level, side by side: program and award, credits required verbatim, requirements compared line by line, and — when the person offers their courses and exam scores — what each school's own published rules would count them for, with GoldCheck's states and reasons carried through unchanged. Credits left is reduced only by items a school's own rules cover; an unknown item, or an inference, never reduces it. Cost, earnings, debt with its 10-year monthly payment beside it, and payback in months where both inputs are published; where either is missing, payback is not computed and the missing input is named. The comparison never ranks: no score is invented to decide for the person.",
"inputSchema": {
"properties": {
"held": {
"description": "Optional: the same shape will_my_credits_transfer takes — an exam { program, exam, score } or a course { unitid or school, code }",
"items": {
"type": "object"
},
"type": "array"
},
"level": {
"description": "The credential level",
"type": "string"
},
"major": {
"description": "The major: a major_minor_id or a CIP code",
"type": "string"
},
"package": {
"description": "Optional: the agent-held GoldRibbon package. GoldSeam stores no copy of it",
"type": "object"
},
"unitids": {
"description": "2 to 5 schools, by IPEDS UNITID",
"examples": [
[
"240505",
"240628"
]
],
"items": {
"type": "string"
},
"type": "array"
}
},
"required": [
"unitids",
"major",
"level"
],
"type": "object"
},
"name": "compare_my_school",
"outputSchema": {
"properties": {
"columns": {
"description": "One column per school: what the person's credits are worth there, credits left, cost, and payback or the input it is missing",
"items": {
"type": "object"
},
"type": "array"
},
"comparison_rule": {
"type": "string"
},
"contract": {
"type": "string"
},
"not_held": {
"items": {
"type": "object"
},
"type": "array"
},
"requirements_side_by_side": {
"description": "compare_program_checklists' own answer, called and not re-implemented",
"type": "object"
},
"statement": {
"type": "string"
},
"understood": {
"type": "object"
}
},
"required": [
"contract",
"statement"
],
"type": "object"
}
},
{
"description": "Compare what a program takes at several institutions: for each IPEDS UNITID, that institution's published checklist for the program (requirement groups, items, published credit strings — the work effort) beside its published tuition and fee policy (the cost). Schedule is stated not held. Nothing is summed or computed by the service; an institution, checklist, or cost the catalogs do not hold is stated as such. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.",
"inputSchema": {
"properties": {
"detail": {
"description": "Optional: full (the default: every requirement group and item) or summary (per checklist its program, award, year, credits and group and item counts, with each school's College Scorecard tuition)",
"examples": [
"summary"
],
"type": "string"
},
"institution_offset": {
"description": "Optional: the next_institution_offset from a previous answer, for the next 5 institutions",
"type": "integer"
},
"program": {
"description": "Program or award words to match, e.g. nursing or Bachelor of Science in Nursing",
"examples": [
"Welding"
],
"type": "string"
},
"unitids": {
"description": "1 to 10 IPEDS UNITIDs, e.g. [\"100663\", \"127060\"]; answered 5 institutions per call, up to 3 checklists each",
"examples": [
[
"225070"
]
],
"items": {
"type": "string"
},
"type": "array"
}
},
"required": [
"unitids",
"program"
],
"type": "object"
},
"name": "compare_program_checklists",
"outputSchema": null
},
{
"description": "What does this code cross to? Auto-detects the family — dotted CIP (52.0201) or dashed SOC (11-1021, O*NET .00 suffix accepted) — and answers the other family's codes and titles from the federal CIP-SOC crosswalk.",
"inputSchema": {
"properties": {
"code": {
"description": "A college program code (CIP, e.g. 51.3801) or an occupation code (SOC, e.g. 29-1141)",
"examples": [
"51.3801",
"29-1141"
],
"type": "string"
},
"limit": {
"description": "Optional page size (default 20, at most 50)",
"type": "integer"
},
"offset": {
"description": "Optional: the next_offset from a previous answer",
"type": "integer"
}
},
"required": [
"code"
],
"type": "object"
},
"name": "crosswalk_code",
"outputSchema": null
},
{
"description": "Draft the credit claims a person's evidence supports, from their package (after my_selfie_ksa_view): each claim quotes the document it rests on. They are drafts for the person to keep, affirm or decline (set each claim's confidence to ratified, affirmed or declined in the package); the AI never affirms a claim. Give the school they are thinking of as `school` so its catalog is made ready for suggest_credit_for_my_learning. Nothing is stored: the answer returns the package for the agent to keep.",
"inputSchema": {
"properties": {
"aspiration": {
"description": "Optional: what the person is aiming for",
"type": "string"
},
"language": {
"enum": [
"en",
"es",
"fr"
],
"type": "string"
},
"package": {
"description": "The goldribbon_package_v1 object an earlier GoldRibbon answer returned. Keep it for the person and send it back whole; GoldSeam keeps no copy.",
"type": "object"
},
"school": {
"description": "Optional: the school they are thinking of, a name or IPEDS UNITID; its catalog is made ready for the suggestions",
"type": "string"
}
},
"required": [
"package"
],
"type": "object"
},
"name": "draft_my_claims",
"outputSchema": {
"properties": {
"claims": {
"description": "The claims drafted by this call, each with summary, source_fragment, kind, evidence_tier, confidence (drafted) and recommendation_mode",
"type": "array"
},
"contract": {
"type": "string"
},
"counts": {
"description": "drafted, answered_kept",
"type": "object"
},
"limits": {
"description": "What this answer could not do, each { code, statement }",
"type": "array"
},
"next_actions": {
"items": {
"properties": {
"arguments": {
"type": "object"
},
"label": {
"type": "string"
},
"tool": {
"description": "A GoldSeam service",
"type": "string"
}
},
"required": [
"label",
"tool",
"arguments"
],
"type": "object"
},
"type": "array"
},
"package": {
"description": "The person's package, with this service's part filled",
"type": "object"
},
"statement": {
"type": "string"
}
},
"required": [
"contract",
"statement"
],
"type": "object"
}
},
{
"description": "What is this word, upward? Walks the WordNet is-a (hypernym) chain meaning to parent meaning, from the word's KSA-mapped sense toward its broader categories, so every step stays in the sense it started in. Each step carries its definition (gloss) and synonyms.",
"inputSchema": {
"properties": {
"term": {
"description": "A word to see what broader kind of thing it is, e.g. carpentry",
"examples": [
"carpentry",
"nursing"
],
"type": "string"
}
},
"required": [
"term"
],
"type": "object"
},
"name": "expand_term",
"outputSchema": null
},
{
"description": "Which articulation or transfer agreements are held? Optional title words, or an institution's UNITID as a party. Answers none held when the build holds none. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.",
"inputSchema": {
"properties": {
"limit": {
"description": "Optional page size (default 20, at most 100)",
"type": "integer"
},
"offset": {
"description": "Optional: the next_offset from a previous answer",
"type": "integer"
},
"query": {
"description": "Optional agreement title words",
"type": "string"
},
"unitid": {
"description": "Optional: an institution party's IPEDS UNITID",
"type": "string"
}
},
"type": "object"
},
"name": "find_agreements",
"outputSchema": null
},
{
"description": "Which published catalog editions are held for this institution? Each catalog's edition year, format and source. Answers none held when the build holds none. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.",
"inputSchema": {
"properties": {
"limit": {
"description": "Optional page size (default 20, at most 100)",
"type": "integer"
},
"offset": {
"description": "Optional: the next_offset from a previous answer",
"type": "integer"
},
"unitid": {
"description": "The institution's IPEDS UNITID, e.g. 225070",
"type": "string"
}
},
"required": [
"unitid"
],
"type": "object"
},
"name": "find_catalogs",
"outputSchema": null
},
{
"description": "Which checklists — the generic itinerary of requirements for an award — does this institution publish? Optional award words or a program id narrow them; pass one to get_checklist. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.",
"inputSchema": {
"properties": {
"limit": {
"description": "Optional page size (default 20, at most 100)",
"type": "integer"
},
"offset": {
"description": "Optional: the next_offset from a previous answer",
"type": "integer"
},
"program_id": {
"description": "Optional: one program's id",
"type": "string"
},
"query": {
"description": "Optional award words, e.g. welding",
"type": "string"
},
"unitid": {
"description": "The institution's IPEDS UNITID",
"examples": [
"225070"
],
"type": "string"
}
},
"required": [
"unitid"
],
"type": "object"
},
"name": "find_checklists",
"outputSchema": null
},
{
"description": "Which comparability bundles (published transfer rules) are held? Optional receiving institution UNITID, agreement id, or a learning unit that appears as a source or substitute. Answers none held when the build holds none. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.",
"inputSchema": {
"properties": {
"agreement_id": {
"description": "Optional: the agreement that states it",
"type": "string"
},
"learning_unit_id": {
"description": "Optional: a course named in it",
"type": "string"
},
"limit": {
"description": "Optional page size (default 20, at most 100)",
"type": "integer"
},
"offset": {
"description": "Optional: the next_offset from a previous answer",
"type": "integer"
},
"unitid": {
"description": "Optional: the receiving institution's IPEDS UNITID",
"type": "string"
}
},
"type": "object"
},
"name": "find_comparability",
"outputSchema": null
},
{
"description": "Which institution is this? A name fragment or an IPEDS UNITID answers with the institution's identity, sector, identifiers with their sources, and how many programs, checklists, and learning units its published catalog holds here. A state lists that state's institutions by name; with no name and no state, the answer is the states that hold institutions, each with its count. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.",
"inputSchema": {
"properties": {
"city": {
"description": "Optional city, one of a state answer's cities, e.g. Denison",
"examples": [
"Denison"
],
"type": "string"
},
"limit": {
"description": "Optional page size (default 20, at most 100)",
"type": "integer"
},
"offset": {
"description": "Optional: the next_offset from a previous answer",
"type": "integer"
},
"query": {
"description": "Name fragment or IPEDS UNITID, e.g. Denver or 127060",
"examples": [
"Grayson",
"225070"
],
"type": "string"
},
"state": {
"description": "Optional two-letter state, e.g. TX: that state's institutions, those with a catalog held first; the answer lists the state's cities",
"examples": [
"TX"
],
"type": "string"
}
},
"type": "object"
},
"name": "find_institution",
"outputSchema": null
},
{
"description": "What's my best way there? For a goal — a major or a job — and what the person brings (courses, exams, their Competency Selfie, work and life experience), the paths to it, each saying WHY it ranks where it does and naming the figures that moved it. The steps appear only where an agreement or pathway document states them, never assembled from award levels alone. Every item the person brought is marked counted, not counted or needs review and appears in the answer: nothing is dropped silently. A path missing an input is ranked with that gap named rather than penalised invisibly.",
"inputSchema": {
"properties": {
"goal": {
"description": "A major (a major_minor_id or CIP) or a job (a SOC code)",
"examples": [
"29-1141"
],
"type": "string"
},
"held": {
"description": "Optional: courses and exams, the shape will_my_credits_transfer takes",
"items": {
"type": "object"
},
"type": "array"
},
"level": {
"description": "The level the person wants",
"type": "string"
},
"limit": {
"description": "Optional page size (default 10, at most 25)",
"type": "integer"
},
"package": {
"description": "Optional: the agent-held GoldRibbon package, read by suggest_credit_for_my_learning. GoldSeam stores no copy",
"type": "object"
},
"state": {
"description": "Optional two-letter state: where they are",
"type": "string"
}
},
"required": [
"goal",
"level"
],
"type": "object"
},
"name": "find_my_best_pathway",
"outputSchema": {
"properties": {
"contract": {
"type": "string"
},
"not_held": {
"items": {
"type": "object"
},
"type": "array"
},
"paths": {
"description": "One per path: school, program, checklist, steps, credits left, cost, payback, and why it ranks where it does",
"items": {
"type": "object"
},
"type": "array"
},
"ranking_rule": {
"type": "string"
},
"statement": {
"type": "string"
},
"steps": {
"description": "Shown only where an agreement or pathway document states them",
"type": "object"
},
"understood": {
"type": "object"
},
"what_you_brought": {
"description": "Every item, marked counted, not counted or needs review, each with its reason",
"items": {
"type": "object"
},
"type": "array"
}
},
"required": [
"contract",
"statement"
],
"type": "object"
}
},
{
"description": "What should I study? For a person's own words — an interest, a subject or a job — or a job code (SOC), the majors that answer. Each major carries its plain definition (NCES verbatim), the award levels it is conferred at (IPEDS AWLEVEL, each completers flag in its own field and never summed), how many schools offer it nationally, the jobs it leads to through the federal CIP-SOC crosswalk, and its related majors — same series, same family, or sharing a named occupation. Words resolve through the KSA Dictionary, never by spelling match; words that match nothing are told so with the closest words the Dictionary holds. The count for a person's own state is stated not held: the per-school IPEDS rows are not in this publish.",
"inputSchema": {
"anyOf": [
{
"required": [
"words"
]
},
{
"required": [
"soc"
]
}
],
"properties": {
"level": {
"description": "Optional award level to narrow to, e.g. certificate, associate or bachelor's",
"type": "string"
},
"limit": {
"description": "Optional page size (default 10, at most 25)",
"type": "integer"
},
"offset": {
"description": "Optional: the offset of the next page",
"type": "integer"
},
"soc": {
"description": "Or a job code (SOC), e.g. 29-1141 for Registered Nurses; every major the federal crosswalk ties to it answers",
"examples": [
"29-1141"
],
"type": "string"
},
"state": {
"description": "Optional two-letter state, for the school counts",
"type": "string"
},
"words": {
"description": "The person's own words: an interest, a subject, or a job, e.g. I like fixing things",
"examples": [
"carpentry"
],
"type": "string"
}
},
"type": "object"
},
"name": "find_my_major",
"outputSchema": {
"properties": {
"contract": {
"type": "string"
},
"majors": {
"description": "One card per major: definition, levels, schools_offering_it, jobs, related_majors — each saying which part is not held",
"items": {
"type": "object"
},
"type": "array"
},
"next_actions": {
"items": {
"properties": {
"arguments": {
"type": "object"
},
"label": {
"type": "string"
},
"tool": {
"description": "A GoldSeam service",
"type": "string"
}
},
"required": [
"label",
"tool",
"arguments"
],
"type": "object"
},
"type": "array"
},
"not_held": {
"description": "The reference tables this publish does not carry, by name",
"items": {
"type": "object"
},
"type": "array"
},
"statement": {
"type": "string"
},
"total_matching": {
"type": "integer"
},
"understood": {
"type": "object"
},
"words_read": {
"description": "How the person's words resolved: the layer each placement came from, and the closest words when nothing matched",
"type": "object"
}
},
"required": [
"contract",
"statement"
],
"type": "object"
}
},
{
"description": "Where can I study this? A match-up, not a dump: for a major and a level, the schools that award it, ranked by how many of the person's own criteria each one meets, with met, not met and not testable kept as three different results — a school that does not publish a fact is not testable on it, never failed. Each criterion names the source that decided it, each school carries its own program, award, credits required, cost, earnings, debt and whether it can be done online, and a filter only ever excludes on a fact we hold. The answer states its ranking rule and never recommends a school. TODAY the candidate set is the schools CourseShelf has captured a program for, not yet every school IPEDS lists, and every answer opens by saying so.",
"inputSchema": {
"properties": {
"also_offers": {
"description": "Optional other subjects or majors the school should also offer",
"items": {
"type": "string"
},
"type": "array"
},
"award": {
"description": "Optional award title or credential class",
"type": "string"
},
"city": {
"description": "Optional city",
"type": "string"
},
"cost_max": {
"description": "Optional: the most the person will pay. A school that publishes no cost is not removed by it — it is ranked below and marked not testable on cost",
"type": "number"
},
"delivery": {
"description": "Optional: in person, hybrid or online",
"type": "string"
},
"exclude_untestable": {
"description": "Optional strict exclusion, off by default: remove schools that do not publish one of the criteria. The answer then says how many were removed and by which criterion",
"type": "boolean"
},
"level": {
"description": "The credential level, e.g. certificate, associate or bachelor's",
"examples": [
"associate"
],
"type": "string"
},
"limit": {
"description": "Optional page size (default 10, at most 25)",
"type": "integer"
},
"major": {
"description": "The major: a major_minor_id (e.g. CIP:51.3801) or a CIP code",
"examples": [
"CIP:51.3801"
],
"type": "string"
},
"near": {
"description": "Optional: a place and a distance, e.g. Casper WY within 50 miles",
"type": "string"
},
"offset": {
"description": "Optional: the offset of the next page",
"type": "integer"
},
"sector": {
"description": "Optional school type as IPEDS labels it, e.g. public 2-year",
"type": "string"
},
"state": {
"description": "Optional two-letter state. With no state, city or place the answer is national and says so",
"type": "string"
},
"with_checklist": {
"description": "Optional: only schools whose requirements CourseShelf holds",
"type": "boolean"
}
},
"required": [
"major",
"level"
],
"type": "object"
},
"name": "find_my_school",
"outputSchema": {
"properties": {
"candidate_set": {
"description": "Where the schools came from and why it is not yet IPEDS's list",
"type": "object"
},
"contract": {
"type": "string"
},
"measure_not_met": {
"description": "The measure this build does not yet meet, named in the answer",
"type": "string"
},
"not_held": {
"items": {
"type": "object"
},
"type": "array"
},
"ranking_rule": {
"type": "string"
},
"schools": {
"description": "One row per school: its program with the route that joined it to the major, cost, earnings and debt, its programs that could not be joined, and its standing — every criterion with its verdict and source",
"items": {
"type": "object"
},
"type": "array"
},
"scope": {
"description": "Said when the answer is national because no place was given",
"type": "string"
},
"statement": {
"description": "What the candidate set is, as the first thing the person reads",
"type": "string"
},
"strict_exclusion": {
"description": "Present only when exclude_untestable was asked for: how many schools were removed, by which criterion",
"type": "object"
},
"understood": {
"type": "object"
}
},
"required": [
"contract",
"statement"
],
"type": "object"
}
},
{
"description": "Which pathways are held? Optional title words, an agreement id, or a checklist id. Answers none held when the build holds none. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.",
"inputSchema": {
"properties": {
"agreement_id": {
"description": "Optional: the agreement a pathway rests on",
"type": "string"
},
"checklist_id": {
"description": "Optional: the checklist a pathway follows",
"type": "string"
},
"limit": {
"description": "Optional page size (default 20, at most 100)",
"type": "integer"
},
"offset": {
"description": "Optional: the next_offset from a previous answer",
"type": "integer"
},
"query": {
"description": "Optional pathway title words",
"type": "string"
}
},
"type": "object"
},
"name": "find_pathways",
"outputSchema": null
},
{
"description": "Which academic policies does this institution publish (transfer credit, prior learning, tuition and fees …)? Optional words narrow them. Answers none held when the build holds none. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.",
"inputSchema": {
"properties": {
"limit": {
"description": "Optional page size (default 20, at most 100)",
"type": "integer"
},
"offset": {
"description": "Optional: the next_offset from a previous answer",
"type": "integer"
},
"query": {
"description": "Optional policy words, e.g. transfer",
"type": "string"
},
"unitid": {
"description": "The institution's IPEDS UNITID, e.g. 225070",
"type": "string"
}
},
"required": [
"unitid"
],
"type": "object"
},
"name": "find_policies",
"outputSchema": null
},
{
"description": "Which programs match these words, across institutions? Program or award words (optionally one institution's UNITID) answer with each program's award, CIP, published credit figure verbatim, edition, source page and institution. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.",
"inputSchema": {
"properties": {
"city": {
"description": "Optional city: programs at that city's institutions",
"type": "string"
},
"limit": {
"description": "Optional page size (default 20, at most 100)",
"type": "integer"
},
"offset": {
"description": "Optional: the next_offset from a previous answer",
"type": "integer"
},
"query": {
"description": "Program or award words, e.g. welding or nursing",
"examples": [
"Welding"
],
"type": "string"
},
"state": {
"description": "Optional two-letter state: programs at that state's institutions",
"type": "string"
},
"unitid": {
"description": "Optional: one institution's IPEDS UNITID",
"type": "string"
}
},
"required": [
"query"
],
"type": "object"
},
"name": "find_programs",
"outputSchema": null
},
{
"description": "Which statewide or compact transfer frameworks are held? Optional name or jurisdiction words. Answers none held when the build holds none. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.",
"inputSchema": {
"properties": {
"limit": {
"description": "Optional page size (default 20, at most 100)",
"type": "integer"
},
"offset": {
"description": "Optional: the next_offset from a previous answer",
"type": "integer"
},
"query": {
"description": "Optional framework name or jurisdiction words",
"type": "string"
}
},
"type": "object"
},
"name": "find_transfer_frameworks",
"outputSchema": null
},
{
"description": "Where can this occupation lead? For a SOC code: destination occupations, each with its typed roads (published by O*NET or by a credential serving both; mapped through the CIP-SOC crosswalk), each road with its source, basis and its class's karat; the bridges (credentials with their exam, education and experience conditions, and programs with checklists nearest the state given); and demand as O*NET publishes it. Roads only, no person data.",
"inputSchema": {
"anyOf": [
{
"required": [
"from_soc"
]
},
{
"required": [
"from"
]
}
],
"properties": {
"class": {
"description": "Optional: only destinations with a road of this class (published, mapped)",
"type": "string"
},
"from": {
"description": "Or the job in everyday words, e.g. welder; several matching occupations answer candidates to pick from",
"type": "string"
},
"from_soc": {
"description": "The occupation's SOC code, e.g. 51-4121 (an O*NET .00 code is accepted)",
"examples": [
"51-4121"
],
"type": "string"
},
"limit": {
"description": "Optional page size (default 10, at most 25)",
"type": "integer"
},
"offset": {
"description": "Optional: the next_offset from a previous answer",
"type": "integer"
},
"prefer": {
"description": "Optional preference such as less physical; answered not held when O*NET work context is not held",
"type": "string"
},
"state": {
"description": "Optional two-letter state for the program bridges",
"type": "string"
}
},
"type": "object"
},
"name": "find_transitions",
"outputSchema": {
"properties": {
"contract": {
"type": "string"
},
"facets": {
"type": "object"
},
"next_actions": {
"items": {
"properties": {
"arguments": {
"type": "object"
},
"label": {
"type": "string"
},
"tool": {
"description": "A GoldSeam service",
"type": "string"
}
},
"required": [
"label",
"tool",
"arguments"
],
"type": "object"
},
"type": "array"
},
"results": {
"description": "The destination cards",
"items": {
"properties": {
"bridges": {
"type": "object"
},
"demand": {
"type": "object"
},
"edges": {
"items": {
"properties": {
"basis": {
"type": "string"
},
"class": {
"type": "string"
},
"karat": {
"type": "string"
},
"source": {
"type": "string"
}
},
"type": "object"
},
"type": "array"
},
"next_actions": {
"items": {
"properties": {
"arguments": {
"type": "object"
},
"label": {
"type": "string"
},
"tool": {
"description": "A GoldSeam service",
"type": "string"
}
},
"required": [
"label",
"tool",
"arguments"
],
"type": "object"
},
"type": "array"
},
"title": {
"type": "string"
},
"to_soc": {
"type": "string"
}
},
"type": "object"
},
"type": "array"
},
"statement": {
"type": "string"
},
"total_matching": {
"type": "integer"
},
"understood": {
"type": "object"
}
},
"required": [
"contract",
"statement"
],
"type": "object"
}
},
{
"description": "One agreement: its row, its parties (organizations resolved), and the pathways, comparability bundles and checklists that cite it. Signatories name people and are not served. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.",
"inputSchema": {
"properties": {
"agreement_id": {
"description": "An agreement id from find_agreements",
"type": "string"
}
},
"required": [
"agreement_id"
],
"type": "object"
},
"name": "get_agreement",
"outputSchema": null
},
{
"description": "One catalog edition: its row, the institutions that use it (and whom it is shared from), and how many programs it holds. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.",
"inputSchema": {
"properties": {
"catalog_id": {
"description": "A catalog id from find_catalogs",
"type": "string"
}
},
"required": [
"catalog_id"
],
"type": "object"
},
"name": "get_catalog",
"outputSchema": null
},
{
"description": "Everything held about one certification: issuer and issuer domain, occupations served, exam and renewal requirements, education-or-experience routes, Credential Engine registry identity where held, and the basis and source URL for the claim.",
"inputSchema": {
"properties": {
"id": {
"description": "A certification id, copied from a search result's id field",
"examples": [
"LU_CERT_ONET_13108200_8F3480AC7A"
],
"type": "string"
}
},
"required": [
"id"
],
"type": "object"
},
"name": "get_certification",
"outputSchema": null
},
{
"description": "What does this award require? One checklist: its requirement groups (every header and full item count), each group's items with published credit strings, alternatives, and — where an item resolved to a course — that course's own code, title, and published credits, attributed to the course. Items come in pages across the groups; the answer states items_total and next_item_offset. Every row names the captured page it came from. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.",
"inputSchema": {
"properties": {
"checklist_id": {
"description": "A checklist id from programs_for_institution or compare_program_checklists",
"examples": [
"CK_225070_05e6e123"
],
"type": "string"
},
"item_limit": {
"description": "Optional items per page (default 60, at most 150)",
"type": "integer"
},
"item_offset": {
"description": "Optional: the next_item_offset from a previous answer",
"type": "integer"
}
},
"required": [
"checklist_id"
],
"type": "object"
},
"name": "get_checklist",
"outputSchema": null
},
{
"description": "One comparability bundle: its row (credits awarded published beside any parse), the receiving institution, and its source and substitute courses, each resolved or stated unresolved. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.",
"inputSchema": {
"properties": {
"comparability_id": {
"description": "A comparability id from find_comparability",
"type": "string"
}
},
"required": [
"comparability_id"
],
"type": "object"
},
"name": "get_comparability",
"outputSchema": null
},
{
"description": "What does CourseShelf hold? From the records published with the build, read as published and never computed: per catalog area, how many institutions have loaded content and how many records were loaded; every table's row count; organizations by sector; the census of the whole index with its verdicts; and per-state counts and per-school verdicts where the build publishes them. Anything not published for this build is said so. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.",
"inputSchema": {
"properties": {},
"type": "object"
},
"name": "get_courseshelf_summary",
"outputSchema": null
},
{
"description": "What does the KSA Dictionary hold? The words and meanings it places, the governed terms, the O*NET content-model elements, the link words and the CIP-SOC crosswalk, each with its own version and build date where the layer publishes one, and an honest not held where it does not. Read as published at boot, never computed at request time, and never a word lookup: for one word use resolve_term. The words it holds are those it places; it is not all of WordNet, and the answer says so.",
"inputSchema": {
"properties": {},
"type": "object"
},
"name": "get_dictionary_summary",
"outputSchema": null
},
{
"description": "Everything held about one institution: its identity row, identifiers, addresses, websites, accreditations, relationships, identity history, published costs and calendar dates, each table under its own name, with counts of its programs, courses, checklists, catalogs, policies and agreements and the service that lists each. Contacts name people and are not served. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.",
"inputSchema": {
"anyOf": [
{
"required": [
"organization_id"
]
},
{
"required": [
"unitid"
]
}
],
"properties": {
"organization_id": {
"description": "The institution's organization id from find_institution, e.g. ORG_225070",
"examples": [
"ORG_225070"
],
"type": "string"
},
"unitid": {
"description": "Or its IPEDS UNITID instead, e.g. 225070",
"type": "string"
}
},
"type": "object"
},
"name": "get_institution",
"outputSchema": null
},
{
"description": "One course whole: its row, prerequisites and corequisites, aliases, terms offered, articulation statements and comparable members — each linked course resolved or stated unresolved, never guessed — plus the transfer frameworks it maps to. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.",
"inputSchema": {
"properties": {
"learning_unit_id": {
"description": "A learning unit id from learning_units or get_checklist",
"examples": [
"LU_course_225070_ENGL1301_20262027"
],
"type": "string"
}
},
"required": [
"learning_unit_id"
],
"type": "object"
},
"name": "get_learning_unit",
"outputSchema": null
},
{
"description": "One pathway: its row and the checklist and agreement it links. Contacts name people and are not served. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.",
"inputSchema": {
"properties": {
"pathway_id": {
"description": "A pathway id from find_pathways",
"type": "string"
}
},
"required": [
"pathway_id"
],
"type": "object"
},
"name": "get_pathway",
"outputSchema": null
},
{
"description": "One published academic policy: its section, verbatim text, page, edition and source. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.",
"inputSchema": {
"properties": {
"policy_id": {
"description": "A policy id from find_policies",
"type": "string"
}
},
"required": [
"policy_id"
],
"type": "object"
},
"name": "get_policy",
"outputSchema": null
},
{
"description": "One program whole: its row, identifiers, offerings (campus resolved), its institution, and the checklists that lead to its award — pass one to get_checklist. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.",
"inputSchema": {
"properties": {
"program_id": {
"description": "A program id from programs_for_institution or find_programs",
"examples": [
"PG_225070_8c96bb26"
],
"type": "string"
}
},
"required": [
"program_id"
],
"type": "object"
},
"name": "get_program",
"outputSchema": null
},
{
"description": "One transfer framework: its row, authority, codes with their meanings, and the courses mapped to it (resolved). Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.",
"inputSchema": {
"properties": {
"framework_id": {
"description": "A framework id from find_transfer_frameworks",
"type": "string"
}
},
"required": [
"framework_id"
],
"type": "object"
},
"name": "get_transfer_framework",
"outputSchema": null
},
{
"description": "What courses does this institution publish? Filter by subject abbreviation, course code (spaces and case ignored), or title words; each course carries its published credit string verbatim (ranges stay ranges), edition, and the captured page. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.",
"inputSchema": {
"properties": {
"code": {
"description": "Optional course code, e.g. BIO 201",
"type": "string"
},
"limit": {
"description": "Optional page size (default 50, at most 100)",
"type": "integer"
},
"offset": {
"description": "Optional: the next_offset from a previous answer",
"type": "integer"
},
"query": {
"description": "Optional title words",
"type": "string"
},
"subject": {
"description": "Optional subject abbreviation, e.g. BIO",
"examples": [
"RNSG"
],
"type": "string"
},
"unit_type": {
"description": "Optional learning-unit type, one of the answer's unit_types, e.g. course",
"type": "string"
},
"unitid": {
"description": "The institution's IPEDS UNITID",
"examples": [
"225070"
],
"type": "string"
}
},
"required": [
"unitid"
],
"type": "object"
},
"name": "learning_units",
"outputSchema": null
},
{
"description": "The issuing organizations, optionally filtered by a name query.",
"inputSchema": {
"properties": {
"limit": {
"description": "Optional page size (default 20, at most 50)",
"type": "integer"
},
"offset": {
"description": "Optional: the next_offset from a previous answer",
"type": "integer"
},
"query": {
"description": "Optional: part of an organization's name",
"examples": [
"IBM",
"nursing"
],
"type": "string"
}
},
"required": [],
"type": "object"
},
"name": "list_issuers",
"outputSchema": null
},
{
"description": "The person's Selfie from their evidence package: the seven dimensions (skills, knowledge, abilities and more) as the evidence shows them, each item citing the file, the occupation O*NET describes, or the life experience it came from, plus what could not be placed. It mirrors, for the person to confirm, refine or reject; it is never a grade or a credit decision. The person's placements and dismissals in the package's selfie.learner_decisions are honored. Nothing is stored: the answer returns the package with the Selfie for the agent to keep.",
"inputSchema": {
"properties": {
"aspiration": {
"description": "Optional: what the person is aiming for",
"type": "string"
},
"language": {
"enum": [
"en",
"es",
"fr"
],
"type": "string"
},
"package": {
"description": "The goldribbon_package_v1 object an earlier GoldRibbon answer returned. Keep it for the person and send it back whole; GoldSeam keeps no copy.",
"type": "object"
}
},
"required": [
"package"
],
"type": "object"
},
"name": "my_selfie_ksa_view",
"outputSchema": {
"properties": {
"contract": {
"type": "string"
},
"evidence_by_source": {
"description": "Each dimension's items grouped by the file, occupation or life experience they came from",
"type": "array"
},
"evidence_truncated": {
"type": "array"
},
"limits": {
"description": "What this answer could not do, each { code, statement }",
"type": "array"
},
"next_actions": {
"items": {
"properties": {
"arguments": {
"type": "object"
},
"label": {
"type": "string"
},
"tool": {
"description": "A GoldSeam service",
"type": "string"
}
},
"required": [
"label",
"tool",
"arguments"
],
"type": "object"
},
"type": "array"
},
"package": {
"description": "The person's package, with this service's part filled",
"type": "object"
},
"selfie": {
"description": "The seven dimensions in canon order, and learner_decisions",
"type": "object"
},
"statement": {
"type": "string"
},
"unresolved_items": {
"type": "array"
}
},
"required": [
"contract",
"statement"
],
"type": "object"
}
},
{
"description": "What occupations does this certification serve?",
"inputSchema": {
"properties": {
"id": {
"description": "A certification id, copied from a search result's id field",
"examples": [
"LU_CERT_ONET_13108200_8F3480AC7A"
],
"type": "string"
},
"limit": {
"description": "Optional page size (default 20, at most 50)",
"type": "integer"
},
"offset": {
"description": "Optional: the next_offset from a previous answer",
"type": "integer"
}
},
"required": [
"id"
],
"type": "object"
},
"name": "occupations_for_certification",
"outputSchema": null
},
{
"description": "What programs does this institution publish? Award, credential class, CIP, the published credit figure verbatim, catalog edition, the captured page each came from, and the checklist ids to pass to get_checklist. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.",
"inputSchema": {
"properties": {
"limit": {
"description": "Optional page size (default 100, at most 200)",
"type": "integer"
},
"offset": {
"description": "Optional: the next_offset from a previous answer",
"type": "integer"
},
"query": {
"description": "Optional program or award words to filter by",
"type": "string"
},
"unitid": {
"description": "The institution's IPEDS UNITID",
"examples": [
"225070"
],
"type": "string"
}
},
"required": [
"unitid"
],
"type": "object"
},
"name": "programs_for_institution",
"outputSchema": null
},
{
"description": "What else serves the same occupation? Traverses on SOC only — a certification sharing solely an instructional program (CIP) is not related (contract § 4).",
"inputSchema": {
"properties": {
"id": {
"description": "A certification id to find others like it, copied from a search result's id field",
"examples": [
"LU_CERT_ONET_29114100_50CD2891D4"
],
"type": "string"
},
"limit": {
"description": "Optional page size (default 20, at most 50)",
"type": "integer"
},
"offset": {
"description": "Optional: the next_offset from a previous answer",
"type": "integer"
}
},
"required": [
"id"
],
"type": "object"
},
"name": "related_certifications",
"outputSchema": null
},
{
"description": "Where does a word place in the KSA model? The KSA Dictionary is the shared vocabulary that defines the terms a learner uses to assert what they know, do, and are — and the terms a learning offering uses to express what it comprises — so both sides resolve to the same identifiers, never spelling matches. Answers from three linked layers (governed lexicon, O*NET content model, WordNet-derived index), each placement attributed to its layer with provenance; the WordNet placement carries the word's definition (gloss) and synonyms.",
"inputSchema": {
"properties": {
"term": {
"description": "A word for something a person knows or can do, e.g. carpentry or mathematics",
"examples": [
"carpentry",
"mathematics",
"welding"
],
"type": "string"
}
},
"required": [
"term"
],
"type": "object"
},
"name": "resolve_term",
"outputSchema": null
},
{
"description": "Which certification is this prose name? Start here for any plain question — a trade, field, job, skill, or company in everyday words. Returns candidates with ids, issuers, and source basis — candidates rather than a single guess when the name is ambiguous; the ids feed the other certification tools.",
"inputSchema": {
"properties": {
"issuer": {
"description": "Optional: only certifications from this organization",
"type": "string"
},
"limit": {
"description": "Optional page size (default 20, at most 50)",
"type": "integer"
},
"offset": {
"description": "Optional: the next_offset from a previous answer",
"type": "integer"
},
"query": {
"description": "What you are looking for, in everyday words — a trade, field, job, or company",
"examples": [
"nursing",
"HVAC",
"welding",
"IBM",
"project management"
],
"type": "string"
}
},
"required": [
"query"
],
"type": "object"
},
"name": "search_certifications",
"outputSchema": {
"properties": {
"certifications": {
"description": "The certification cards",
"items": {
"properties": {
"id": {
"type": "string"
},
"name": {
"type": "string"
},
"next_actions": {
"items": {
"properties": {
"arguments": {
"type": "object"
},
"label": {
"type": "string"
},
"tool": {
"description": "A GoldSeam service",
"type": "string"
}
},
"required": [
"label",
"tool",
"arguments"
],
"type": "object"
},
"type": "array"
},
"type": {
"type": "string"
}
},
"type": "object"
},
"type": "array"
},
"contract": {
"type": "string"
},
"next_actions": {
"items": {
"properties": {
"arguments": {
"type": "object"
},
"label": {
"type": "string"
},
"tool": {
"description": "A GoldSeam service",
"type": "string"
}
},
"required": [
"label",
"tool",
"arguments"
],
"type": "object"
},
"type": "array"
},
"next_offset": {
"type": "integer"
},
"portal_url": {
"description": "The same search on the portal",
"type": "string"
},
"statement": {
"type": "string"
},
"total_matching": {
"type": "integer"
},
"understood": {
"description": "What was read: words, issuer, and match (step, matched_terms, statement)",
"type": "object"
}
},
"required": [
"contract"
],
"type": "object"
}
},
{
"description": "Which programs or courses match, and where? Words, a subject (CIP family, or unknown), a course subject prefix, a credential class, an award as published, and a school's state, city, type or UNITID answer with product cards (name, award, length and college when held, school and city, subject, checklist size, and what the program leads to through the CIP-SOC crosswalk) and the counts to refine by. Courses across every school need words of 3 or more characters; words held by very many courses need a state, city or school. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.",
"inputSchema": {
"properties": {
"award": {
"description": "Optional award exactly as published, one of the answer's awards",
"examples": [
"Certificate"
],
"type": "string"
},
"cip": {
"description": "Optional: programs with this six-digit CIP code (e.g. 48.0508), a comma-separated list, or an array of codes"
},
"city": {
"description": "Optional city, one of a state answer's cities",
"type": "string"
},
"code": {
"description": "Optional, courses only: a course code as printed, e.g. ZOO 2015; lists that code at every school, or within the state, city or school given",
"type": "string"
},
"credential": {
"description": "Optional, programs only: a credential class, one of the answer's credential values (e.g. ceterms:AssociateDegree), or none",
"type": "string"
},
"limit": {
"description": "Optional page size (default 10, at most 50)",
"type": "integer"
},
"offset": {
"description": "Optional: the next_offset from a previous answer",
"type": "integer"
},
"place": {
"description": "Optional: a place the question names, read as a state (name or code), a city, or a school, e.g. Wyoming or Casper",
"type": "string"
},
"query": {
"description": "Words: a program's name or award, or a course's title",
"examples": [
"nursing"
],
"type": "string"
},
"sector": {
"description": "Optional school type as IPEDS labels it, e.g. public 2-year",
"type": "string"
},
"state": {
"description": "Optional two-letter state",
"examples": [
"TX"
],
"type": "string"
},
"subject": {
"description": "Optional CIP family (two digits, e.g. 51) or unknown",
"type": "string"
},
"subject_code": {
"description": "Optional: a course subject prefix, e.g. NURS, one of the answer's subject codes. A course's own prefix as printed, or a prefix a program's checklist requires",
"type": "string"
},
"type": {
"description": "program (the default) or learning_unit",
"examples": [
"program"
],
"type": "string"
},
"unitid": {
"description": "Optional: one school's IPEDS UNITID",
"type": "string"
}
},
"type": "object"
},
"name": "search_programs_and_learning_units",
"outputSchema": {
"properties": {
"build_version": {
"description": "Deprecated: the same value as publish",
"type": "integer"
},
"census_cleared": {
"type": "boolean"
},
"contract": {
"type": "string"
},
"facets": {
"description": "The refinements: each facet's values with their counts of held rows",
"type": "object"
},
"next_actions": {
"items": {
"properties": {
"arguments": {
"type": "object"
},
"label": {
"type": "string"
},
"tool": {
"description": "A GoldSeam service",
"type": "string"
}
},
"required": [
"label",
"tool",
"arguments"
],
"type": "object"
},
"type": "array"
},
"next_offset": {
"type": "integer"
},
"portal_url": {
"description": "The same view on the portal",
"type": "string"
},
"publish": {
"description": "The data road's publish number",
"type": "integer"
},
"results": {
"description": "The product cards",
"items": {
"properties": {
"award": {
"description": "The award as published, or null"
},
"checklist": {
"description": "checklist_id, requirements, credits_computed; or null"
},
"college": {
"description": "The college within the school that offers the program, when held",
"type": "string"
},
"credits_published": {
"description": "A course's credits as printed, when held",
"type": "string"
},
"description_excerpt": {
"description": "A course description's first 200 characters, with an ellipsis when longer; the full text is on get_learning_unit",
"type": "string"
},
"first_edition_seen": {
"description": "The earliest academic year a source prints it in; absent for a record with one form and one source",
"type": "string"
},
"form_statement": {
"description": "One sentence about the record's forms and sources, and whether it was last seen in an older edition",
"type": "string"
},
"id": {
"type": "string"
},
"last_edition_seen": {
"description": "The latest academic year a source prints it in; absent for a record with one form and one source",
"type": "string"
},
"leads_to": {
"description": "occupations through the CIP-SOC crosswalk; absent when none is held",
"type": "object"
},
"name": {
"type": "string"
},
"next_actions": {
"items": {
"properties": {
"arguments": {
"type": "object"
},
"label": {
"type": "string"
},
"tool": {
"description": "A GoldSeam service",
"type": "string"
}
},
"required": [
"label",
"tool",
"arguments"
],
"type": "object"
},
"type": "array"
},
"normal_length": {
"description": "A program's normal length as published, when held",
"type": "string"
},
"school": {
"description": "name, city, state, sector, ipeds_unit_id",
"type": "object"
},
"source_count": {
"description": "How many sources print the record; absent for a record with one form and one source",
"type": "integer"
},
"subject": {
"description": "cip_code, family, family_title, cip_source; absent when the program holds no CIP",
"type": "object"
},
"type": {
"description": "program or learning_unit",
"type": "string"
},
"version_count": {
"description": "How many FORMS the record holds; absent for a record with one form and one source",
"type": "integer"
}
},
"type": "object"
},
"type": "array"
},
"schools_matching": {
"description": "How many schools hold the matching set",
"type": "integer"
},
"statement": {
"type": "string"
},
"total_matching": {
"type": "integer"
},
"understood": {
"description": "What was read: words, place (with candidates when several schools fit), the filters in force, question (frame, department, not_held words), lead (the product a page shows first), and match (step, words_used, stems, statement)",
"type": "object"
},
"union_statement": {
"description": "Said once when any card carries forms or sources: the full source list is in the structured data",
"type": "string"
}
},
"required": [
"contract",
"build_version",
"census_cleared",
"statement"
],
"type": "object"
}
},
{
"description": "Where is a person in the program they are aiming for, and what may their learning meet? Name the program with `checklist_id` (find it with find_programs at that school) and the answer is that program's checklist line by line: the lines their claims may meet, each with the claim, how well it is corroborated and every link cited; the lines a transfer answer in their package already covers; and the lines still needed. Learning no line matches stands as block credit. Without a program, no course is suggested and the claims stand as block credit. Each suggestion is a case to put to the school's prior learning review, never a promise: say may, never will. Nothing is stored: the answer returns the package with the suggestions for the agent to keep.",
"inputSchema": {
"properties": {
"aspiration": {
"description": "Optional: what the person is aiming for",
"type": "string"
},
"checklist_id": {
"description": "The program the person is aiming for, from find_programs or find_checklists at that school. Its lines are the only courses considered; without it no course is suggested.",
"examples": [
"CK_225070_05e6e123"
],
"type": "string"
},
"language": {
"enum": [
"en",
"es",
"fr"
],
"type": "string"
},
"package": {
"description": "The goldribbon_package_v1 object an earlier GoldRibbon answer returned. Keep it for the person and send it back whole; GoldSeam keeps no copy.",
"type": "object"
},
"target_unitid": {
"description": "The school's IPEDS UNITID, e.g. 240620",
"examples": [
"240620"
],
"type": "string"
}
},
"required": [
"package",
"target_unitid"
],
"type": "object"
},
"name": "suggest_credit_for_my_learning",
"outputSchema": {
"properties": {
"contract": {
"type": "string"
},
"counts": {
"description": "claims, comparable_courses, block_credits, checklist_lines, may_be_met, already_covered, still_needed",
"type": "object"
},
"limits": {
"description": "What this answer could not do, each { code, statement }",
"type": "array"
},
"next_actions": {
"items": {
"properties": {
"arguments": {
"type": "object"
},
"label": {
"type": "string"
},
"tool": {
"description": "A GoldSeam service",
"type": "string"
}
},
"required": [
"label",
"tool",
"arguments"
],
"type": "object"
},
"type": "array"
},
"package": {
"description": "The person's package, with this service's part filled",
"type": "object"
},
"statement": {
"type": "string"
},
"suggestions": {
"description": "unitid, school, checklist_id, program, checklist (every line in its own order, each may_be_met with the claim, band and cited chain, already_covered, or still_needed), comparable_courses, block_credits, affirmed_not_pursued",
"type": "object"
}
},
"required": [
"contract",
"statement"
],
"type": "object"
}
},
{
"description": "Will my prior credits apply as credit at my target school? For each thing a person holds (an AP, CLEP or IB exam and its score, or a course taken at a school) the target school's own published transfer rules (CourseAtlas) and CollegeBoard's reported AP policy, in three states: covered (a rule carries it to a course at the target), missing (the target's own rule needs a higher score), unknown (no rule held; never a guess). Each covered item names the course it lands as, every rule with its minimum score and dates, how many rules agree, and the target's programs whose checklists require that course. A case to argue, not a verdict; recognition is the school's act. Each row names its current FORM's wording source: source_url, capture_file, catalog_year and source_catalog_name are that one source's, never the record's whole span. A row whose record holds more than one form or more than one source also carries version_count, source_count, first_edition_seen and last_edition_seen, and one sentence saying so in words; a record with one form and one source carries none of them and reads exactly as it always has. The forms themselves, each with its own content and its own sources, come from the one-record get, never from a list. A record last seen in an older edition says so, because the Union keeps a record no current catalog prints.",
"inputSchema": {
"properties": {
"checklist_id": {
"description": "Optional: the target program's checklist id; the answer then names the lines each covered item addresses",
"type": "string"
},
"held": {
"description": "1 to 20 things held: an exam { program: AP|CLEP|IB, exam: its code (e.g. AP 3700) or title (e.g. United States History), score }, or a course { unitid or school, code as printed (e.g. HIS 110) }",
"examples": [
[
{
"exam": "United States History",
"program": "AP",
"score": 3
}
]
],
"items": {
"type": "object"
},
"type": "array"
},
"target_unitid": {
"description": "The target school's IPEDS UNITID, e.g. 216038",
"examples": [
"216038"
],
"type": "string"
}
},
"required": [
"held",
"target_unitid"
],
"type": "object"
},
"name": "will_my_credits_transfer",
"outputSchema": {
"properties": {
"contract": {
"type": "string"
},
"counts": {
"description": "covered, missing, unknown",
"type": "object"
},
"items": {
"description": "One per held item: held, read_as, state (covered|missing|unknown), reason, lands_as (course, learning_unit_id, rules, corroboration, band, satisfies), statement",
"items": {
"type": "object"
},
"type": "array"
},
"limits": {
"description": "What this answer could not do, each { code, statement }",
"type": "array"
},
"next_actions": {
"items": {
"properties": {
"arguments": {
"type": "object"
},
"label": {
"type": "string"
},
"tool": {
"description": "A GoldSeam service",
"type": "string"
}
},
"required": [
"label",
"tool",
"arguments"
],
"type": "object"
},
"type": "array"
},
"statement": {
"type": "string"
},
"target": {
"type": "object"
},
"understood": {
"type": "object"
}
},
"required": [
"contract",
"statement"
],
"type": "object"
}
}
]
}Verify it yourself
curl -s https://api.teppi.xyz/v1/evidence/sha256:c67856c3089fae3e713422000b8b56eb4acdb3590f9874ec24af9fab9222968c | sha256sum