Server definition
- Hash
- sha256:2505f92282514139fd2cd2fca684b013b6278201ce033812e39cd24242b400a3
- What it is
- What a remote MCP server returned when asked what it offers: 87 tools
The blob, as servednamed by its sha256
{
"instructions": null,
"tools": [
{
"description": "Find all access pathways for a GLP-1 drug (Ozempic, Wegovy, Mounjaro, Zepbound) given patient eligibility factors. Ranks pathways by monthly cost, flags prior-authorization rules and step-therapy, and returns the recommended appeal strategy if denial is likely.\n\nWHEN TO USE: User specifically asks about GLP-1 drugs (Ozempic, Wegovy, Mounjaro, Zepbound) — coverage, prior-auth strategy, step-therapy alternatives.\n\nWHEN NOT: For non-GLP-1 prescriptions (use optimize_prescription).",
"inputSchema": {
"properties": {
"bmi": {
"type": "number"
},
"current_copay": {
"type": "number"
},
"has_cvd": {
"type": "boolean"
},
"has_diabetes": {
"type": "boolean"
},
"insurer": {
"type": "string"
},
"medicare": {
"type": "boolean"
},
"state": {
"type": "string"
},
"tried_step_therapy": {
"description": "Drug names already tried under step therapy, e.g. ['metformin'].",
"items": {
"type": "string"
},
"type": "array"
}
},
"required": [
"insurer",
"bmi"
],
"type": "object"
},
"name": "analyze_glp1_pathways",
"outputSchema": null
},
{
"description": "[Taxonomy VII.120 — baseline response (public data only)] Generate component arguments for an appeal letter: medical-necessity, contract, policy.\n\nWHEN TO USE: User has a denied claim and wants to appeal, or is preparing arguments / evidence / escalation steps for one.\n\nWHEN NOT: For explaining what a denial code means without drafting an appeal, use denial_code_explainer first. For finding a negotiation path on a non-denied bill, use negotiate_bill_script.\n\nEXAMPLES:\n- Argument blocks for CO-50 with UHC: `{\"denial_code\":\"CO-50\",\"insurer\":\"UnitedHealthcare\"}`",
"inputSchema": {
"properties": {
"cpt_code": {
"type": "string"
},
"denial_code": {
"type": "string"
},
"icd10_code": {
"type": "string"
},
"insurer": {
"type": "string"
}
},
"type": "object"
},
"name": "appeal_argument_generator",
"outputSchema": null
},
{
"description": "[Taxonomy VII.129 — baseline response (public data only)] Find the correct escalation path for a denied claim (internal appeal → external review → DOI).\n\nWHEN TO USE: User needs to know the deadlines and agencies for each step of appealing a denial. Pass state (e.g. 'CA') and insurer for state-specific and insurer-specific values.\n\nWHEN NOT: Without state/insurer — still works but returns generic federal defaults. Follow up with state for best answer.\n\nEXAMPLES:\n- CA / UnitedHealthcare escalation path: `{\"state\":\"CA\",\"insurer\":\"UnitedHealthcare\"}`",
"inputSchema": {
"properties": {
"insurer": {
"description": "Insurer canonical name, e.g. 'UnitedHealthcare', 'Aetna'. Used to look up payer-specific appeal windows.",
"type": "string"
},
"state": {
"description": "Two-letter US state code. State-specific external-review deadlines and DOI agency URL are returned when we have them (top 16 states).",
"type": "string"
}
},
"type": "object"
},
"name": "appeal_escalation_path_finder",
"outputSchema": null
},
{
"description": "[Taxonomy E.25 — delegates to estimate_appeal_success] Given a denial, predict the probability of a successful appeal. Returns probability with 95% CI, sample size, and recommended appeal-strategy tags.\n\nWHEN TO USE: User or caller wants a probabilistic estimate (denial likelihood, appeal success, payment delay, etc.) to decide whether to pursue a path.\n\nWHEN NOT: For hard facts (dollar amounts, code definitions, deadlines). Predictions carry confidence bands; call out the uncertainty when you relay the number.",
"inputSchema": {
"properties": {
"cpt_code": {
"type": "string"
},
"denial_reason": {
"type": "string"
},
"insurer": {
"type": "string"
},
"state": {
"type": "string"
}
},
"required": [
"insurer",
"denial_reason",
"cpt_code"
],
"type": "object"
},
"name": "appeal_success_predictor",
"outputSchema": null
},
{
"description": "Scan multiple medical bills in one call. Returns per-bill anomaly lists + total recovery estimate across the batch. Input is a list of {bill_text, provider?, insurer?} items (max 10 per call). Much faster than serial scan_bill_for_errors when handling a bulk upload.\n\nWHEN TO USE: User has multiple bills or EOBs to review at once (e.g. a family's bills from one visit, or a year of statements).\n\nWHEN NOT: For a single bill (use scan_bill_for_errors).",
"inputSchema": {
"properties": {
"bills": {
"items": {
"properties": {
"bill_text": {
"maxLength": 50000,
"type": "string"
},
"insurer": {
"maxLength": 100,
"type": "string"
},
"provider": {
"maxLength": 200,
"type": "string"
}
},
"required": [
"bill_text"
],
"type": "object"
},
"maxItems": 10,
"type": "array"
}
},
"required": [
"bills"
],
"type": "object"
},
"name": "batch_scan_bills",
"outputSchema": null
},
{
"description": "[Taxonomy X.179 — baseline response (public data only)] Predict risk that a planned service will trigger an unexpected large bill.\n\nWHEN TO USE: User planning a service and wants to know if it will trigger an unexpected-large-bill situation. Pass expected_charge_usd and optionally cpt_code to get Medicare-ratio context.\n\nWHEN NOT: For a bill already received — scan_bill_for_errors first.\n\nEXAMPLES:\n- Check shock risk on $5,000 office visit: `{\"expected_charge_usd\":5000,\"cpt_code\":\"99213\"}`",
"inputSchema": {
"properties": {
"cpt_code": {
"description": "Optional CPT code; when provided, the response includes the Medicare national rate and charge-to-Medicare ratio.",
"type": "string"
},
"expected_charge_usd": {
"description": "The expected out-of-pocket charge in USD (no currency symbol).",
"type": "number"
},
"threshold_usd": {
"description": "Override the default shock threshold (default = KFF 2024 average individual deductible = $1,735).",
"type": "number"
}
},
"required": [
"expected_charge_usd"
],
"type": "object"
},
"name": "bill_shock_predictor",
"outputSchema": null
},
{
"description": "[Taxonomy III.51 — baseline response (public data only)] Delta between billed charge and payer-allowed amount for a claim line.\n\nWHEN TO USE: User wants to understand what a service typically costs, compare prices across regions/providers, or gauge whether a billed amount is reasonable.\n\nWHEN NOT: For a specific bill they have in hand, scan_bill_for_errors is more actionable. For insurance-path estimates, use deductible_impact_calculator or coinsurance_simulator.",
"inputSchema": {
"properties": {
"allowed_usd": {
"type": "number"
},
"billed_usd": {
"type": "number"
}
},
"required": [
"billed_usd",
"allowed_usd"
],
"type": "object"
},
"name": "billing_charge_vs_allowed_delta",
"outputSchema": null
},
{
"description": "[Taxonomy C.16 — delegates to scan_bill_for_errors] Detect CPT unbundling (billing components of a procedure separately to inflate the claim). Uses the CMS NCCI edits plus payer-specific bundling rules.\n\nWHEN TO USE: Caller is building or validating a claim payload before submission — format, structure, completeness, alignment.\n\nWHEN NOT: For an already-submitted and denied claim, use generate_appeal_letter. For market pricing context, use benchmark_payer_rate.",
"inputSchema": {
"properties": {
"cpt_codes": {
"items": {
"type": "string"
},
"type": "array"
},
"dos": {
"description": "Date of service, YYYY-MM-DD.",
"type": "string"
},
"payer": {
"type": "string"
}
},
"required": [
"cpt_codes"
],
"type": "object"
},
"name": "bundling_violation_detector",
"outputSchema": null
},
{
"description": "[Taxonomy III.39 — baseline response (public data only)] Estimate a fair cash price for a service in a given region (no-insurance path).\n\nWHEN TO USE: Uninsured/self-pay user wants a fair-market cash price for a service. Returns Medicare national as a floor + commercial-multiple band.\n\nWHEN NOT: For insurance-covered scenarios (deductible_impact_calculator + coinsurance_simulator).\n\nEXAMPLES:\n- Cash price for office visit: `{\"cpt_code\":\"99213\",\"zip3\":\"902\"}`",
"inputSchema": {
"properties": {
"cpt_code": {
"type": "string"
},
"zip3": {
"type": "string"
}
},
"required": [
"cpt_code"
],
"type": "object"
},
"name": "cash_price_estimator",
"outputSchema": null
},
{
"description": "[Taxonomy H.41 — baseline response (public data only)] For a given service + patient plan, determine whether cash-pay + charity-care beats insurance billing.\n\nWHEN TO USE: User is planning for a medical expense, comparing plan options, looking for financial assistance, or trying to structure a payment plan.\n\nWHEN NOT: For billing-error analysis (scan_bill_for_errors) or appeal drafting (generate_appeal_letter).",
"inputSchema": {
"properties": {
"cash_price": {
"type": "number"
},
"cpt_code": {
"type": "string"
},
"deductible_remaining": {
"type": "number"
},
"insurance_cost_estimate": {
"type": "number"
}
},
"required": [
"cpt_code"
],
"type": "object"
},
"name": "cash_vs_insurance_optimizer",
"outputSchema": null
},
{
"description": "[Taxonomy C.14 — delegates to scan_bill_for_errors] Detect internal contradictions in a claim: time mismatches, mutually exclusive codes, missing required fields, patient-gender/procedure mismatches.\n\nWHEN TO USE: Caller is building or validating a claim payload before submission — format, structure, completeness, alignment.\n\nWHEN NOT: For an already-submitted and denied claim, use generate_appeal_letter. For market pricing context, use benchmark_payer_rate.",
"inputSchema": {
"properties": {
"claim_payload": {
"description": "Structured claim (CPT + ICD + dates + amounts).",
"type": "object"
}
},
"required": [
"claim_payload"
],
"type": "object"
},
"name": "claim_consistency_checker",
"outputSchema": null
},
{
"description": "[Taxonomy IV.75 — baseline response (public data only)] Detect duplicated service lines within a single claim.\n\nWHEN TO USE: Caller is building or validating a claim payload before submission — format, structure, completeness, alignment.\n\nWHEN NOT: For an already-submitted and denied claim, use generate_appeal_letter. For market pricing context, use benchmark_payer_rate.",
"inputSchema": {
"properties": {
"claim": {
"type": "object"
}
},
"required": [
"claim"
],
"type": "object"
},
"name": "claim_duplicate_line_detector",
"outputSchema": null
},
{
"description": "[Taxonomy VII.128 — baseline response (public data only)] Generate a rebuttal to a payer's denial rationale point-by-point.\n\nWHEN TO USE: User has a denied claim and wants to appeal, or is preparing arguments / evidence / escalation steps for one.\n\nWHEN NOT: For explaining what a denial code means without drafting an appeal, use denial_code_explainer first. For finding a negotiation path on a non-denied bill, use negotiate_bill_script.",
"inputSchema": {
"additionalProperties": true,
"properties": {},
"type": "object"
},
"name": "claim_rebuttal_generator",
"outputSchema": null
},
{
"description": "[Taxonomy VII.132 — baseline response (public data only)] Build a claim reconsideration request (lighter-weight than a formal appeal).\n\nWHEN TO USE: User has a denied claim and wants to appeal, or is preparing arguments / evidence / escalation steps for one.\n\nWHEN NOT: For explaining what a denial code means without drafting an appeal, use denial_code_explainer first. For finding a negotiation path on a non-denied bill, use negotiate_bill_script.",
"inputSchema": {
"additionalProperties": true,
"properties": {},
"type": "object"
},
"name": "claim_reconsideration_builder",
"outputSchema": null
},
{
"description": "[Taxonomy II.25 — baseline response (public data only)] Check a set of CPT codes against NCCI bundling rules (distinct from modifier-based unbundling).\n\nWHEN TO USE: User asks about medical codes: what a CPT/ICD/HCPCS code means, whether a code combination is valid, or how to map between them.\n\nWHEN NOT: For full bill scans (use scan_bill_for_errors). For appealing a coding-related denial (use generate_appeal_letter).",
"inputSchema": {
"properties": {
"cpt_codes": {
"description": "Array of CPT codes to check for NCCI bundling violations.",
"items": {
"type": "string"
},
"type": "array"
}
},
"required": [
"cpt_codes"
],
"type": "object"
},
"name": "code_bundle_validator",
"outputSchema": null
},
{
"description": "[Taxonomy A.5 — delegates to scan_bill_for_errors] Detect CPT unbundling, mutually exclusive code pairs, and NCCI edit violations in a set of codes. Implemented by the bill scanner's anomaly engine.\n\nWHEN TO USE: User asks about medical codes: what a CPT/ICD/HCPCS code means, whether a code combination is valid, or how to map between them.\n\nWHEN NOT: For full bill scans (use scan_bill_for_errors). For appealing a coding-related denial (use generate_appeal_letter).",
"inputSchema": {
"properties": {
"cpt_codes": {
"description": "Array of CPT codes to check for conflicts.",
"items": {
"type": "string"
},
"type": "array"
},
"icd10_codes": {
"description": "Optional diagnosis codes for medical-necessity conflict checks.",
"items": {
"type": "string"
},
"type": "array"
}
},
"required": [
"cpt_codes"
],
"type": "object"
},
"name": "code_conflict_detector",
"outputSchema": null
},
{
"description": "[Taxonomy III.49 — baseline response (public data only)] Simulate member coinsurance exposure across plan-design variants.\n\nWHEN TO USE: User wants to model their coinsurance share of a post-deductible charge. Pass charge_usd and optionally coinsurance_rate.\n\nWHEN NOT: For flat-copay services (copay_model).\n\nEXAMPLES:\n- Simulate 20% coinsurance on $1K: `{\"charge_usd\":1000,\"coinsurance_rate\":0.2}`",
"inputSchema": {
"properties": {
"charge_usd": {
"type": "number"
},
"coinsurance_rate": {
"description": "Coinsurance rate as a decimal (e.g. 0.20 for 20%). Default is KFF 2024 avg (18%).",
"maximum": 1,
"minimum": 0,
"type": "number"
}
},
"required": [
"charge_usd"
],
"type": "object"
},
"name": "coinsurance_simulator",
"outputSchema": null
},
{
"description": "[Taxonomy III.50 — baseline response (public data only)] Model member copay for a service by plan-design class.\n\nWHEN TO USE: User wants the typical copay for a service type (primary / specialist / er). Uses KFF EHBS 2024 averages.\n\nWHEN NOT: For patient-specific plan details — copay varies by plan design.\n\nEXAMPLES:\n- Typical specialist copay: `{\"service_type\":\"specialist\"}`",
"inputSchema": {
"properties": {
"service_type": {
"description": "Service category. Returns KFF EHBS 2024 average copay for that category.",
"enum": [
"primary",
"specialist",
"er",
"emergency"
],
"type": "string"
}
},
"type": "object"
},
"name": "copay_model",
"outputSchema": null
},
{
"description": "[Taxonomy II.21 — baseline response (public data only)] For a given CPT, surface the ICD-10 codes typically paired with it for medical-necessity support.\n\nWHEN TO USE: User has a CPT code and wants to know what ICD-10 diagnoses commonly pair with it for medical-necessity support.\n\nWHEN NOT: For specific payer policy lookups (code_validation).\n\nEXAMPLES:\n- Common ICDs for 99213: `{\"cpt_code\":\"99213\"}`",
"inputSchema": {
"properties": {
"cpt_code": {
"description": "Single CPT/HCPCS code, e.g. '99213'. Returns common ICD-10 pairings from the public co-occurrence table.",
"type": "string"
}
},
"required": [
"cpt_code"
],
"type": "object"
},
"name": "cpt_to_icd_mapper",
"outputSchema": null
},
{
"description": "Decode a CARC (Claim Adjustment Reason Code) denial code into plain English. Returns meaning, category, whether it's typically reversible on appeal, and appeal guidance. Source: public X12 External Code List + CMS/ERISA public rules. Free, no auth.\n\nWHEN TO USE: Reference lookups: individual code details, verifying a provider registry entry, checking a prior Medigami response's signature, or tracking an outcome.\n\nWHEN NOT: For composite workflows use the higher-level tool that calls these internally.",
"inputSchema": {
"properties": {
"carc_code": {
"description": "CARC/RARC code, e.g. 'CO-16', '16', 'CO-50'.",
"maxLength": 20,
"type": "string"
}
},
"required": [
"carc_code"
],
"type": "object"
},
"name": "decode_denial",
"outputSchema": null
},
{
"description": "[Taxonomy III.48 — baseline response (public data only)] Estimate how a planned service will draw against the member's deductible.\n\nWHEN TO USE: User wants to know how a specific charge affects their deductible (how much draws down, remaining after, post-deductible exposure).\n\nWHEN NOT: For total annual out-of-pocket across a year (healthcare_budget_forecaster).\n\nEXAMPLES:\n- Compute deductible drawdown for $4K charge: `{\"charge_usd\":4000,\"deductible_remaining_usd\":1735}`",
"inputSchema": {
"properties": {
"charge_usd": {
"type": "number"
},
"deductible_remaining_usd": {
"type": "number"
}
},
"required": [
"charge_usd"
],
"type": "object"
},
"name": "deductible_impact_calculator",
"outputSchema": null
},
{
"description": "[Taxonomy VII.131 — baseline response (public data only)] Explain a CARC/RARC denial code in plain language with common causes.\n\nWHEN TO USE: User asks 'what does CO-16 mean' or similar — any CARC/RARC code. Returns full X12 table entry when available with meaning, category, typical root cause, primary remediation, and reversibility flag.\n\nWHEN NOT: For drafting an appeal (generate_appeal_letter). For the full escalation path (appeal_escalation_path_finder).\n\nEXAMPLES:\n- Explain CARC CO-16: `{\"code\":\"CO-16\"}`\n- Explain CARC CO-50 (medical necessity): `{\"code\":\"CO-50\"}`",
"inputSchema": {
"properties": {
"code": {
"description": "CARC/RARC denial code only, e.g. 'CO-16', 'CO-50', 'PR-1'. The tool looks up the code in the public X12 table. Passing the full expanded reason is tolerated (prefix extracted automatically) but the short code is preferred.",
"type": "string"
}
},
"required": [
"code"
],
"type": "object"
},
"name": "denial_code_explainer",
"outputSchema": null
},
{
"description": "[Taxonomy VI.106 — baseline response (public data only)] Classify a denial letter or remittance advice into normalized denial-reason categories.\n\nWHEN TO USE: User or caller wants a probabilistic estimate (denial likelihood, appeal success, payment delay, etc.) to decide whether to pursue a path.\n\nWHEN NOT: For hard facts (dollar amounts, code definitions, deadlines). Predictions carry confidence bands; call out the uncertainty when you relay the number.",
"inputSchema": {
"additionalProperties": true,
"properties": {},
"type": "object"
},
"name": "denial_reason_classifier",
"outputSchema": null
},
{
"description": "[Taxonomy VII.121 — baseline response (public data only)] Build a denial-response package tailored to the denial reason code.\n\nWHEN TO USE: User has a denied claim and wants to appeal, or is preparing arguments / evidence / escalation steps for one.\n\nWHEN NOT: For explaining what a denial code means without drafting an appeal, use denial_code_explainer first. For finding a negotiation path on a non-denied bill, use negotiate_bill_script.\n\nEXAMPLES:\n- Build response package for CO-197: `{\"denial_reason\":\"CO-197\",\"insurer\":\"Aetna\",\"cpt_code\":\"45378\",\"amount\":1850}`",
"inputSchema": {
"properties": {
"amount": {
"type": "number"
},
"cpt_code": {
"type": "string"
},
"denial_reason": {
"description": "CARC denial code, e.g. 'CO-16'.",
"type": "string"
},
"insurer": {
"type": "string"
}
},
"type": "object"
},
"name": "denial_response_builder",
"outputSchema": null
},
{
"description": "[Taxonomy VII.123 — baseline response (public data only)] Assemble a complete dispute case file including claim, denial, evidence, and timeline.\n\nWHEN TO USE: User has a denied claim and wants to appeal, or is preparing arguments / evidence / escalation steps for one.\n\nWHEN NOT: For explaining what a denial code means without drafting an appeal, use denial_code_explainer first. For finding a negotiation path on a non-denied bill, use negotiate_bill_script.",
"inputSchema": {
"additionalProperties": true,
"properties": {},
"type": "object"
},
"name": "dispute_case_builder",
"outputSchema": null
},
{
"description": "Probability an appeal will be approved, derived from outcome-labeled data weighted by label provenance (IRO determinations, EOB reversals, physician confirmations). Returns probability + 95% CI + sample_size + expected_days_to_resolution + tracking_id. Report the actual outcome later via POST /api/outcomes/record with the same tracking_id to improve future estimates.\n\nWHEN TO USE: User or caller wants probability-of-reversal before spending time on an appeal. Returns probability + confidence interval.\n\nWHEN NOT: For picking among multiple appeal strategies (appeal_strategy_success_model). As a stand-alone — usually chain into generate_appeal_letter.\n\nEXAMPLES:\n- Gauge CO-50 appeal odds on Aetna: `{\"insurer\":\"Aetna\",\"denial_reason\":\"CO-50\",\"cpt_code\":\"72148\",\"state\":\"TX\",\"amount\":1200}`",
"inputSchema": {
"properties": {
"amount": {
"type": "number"
},
"cpt_code": {
"type": "string"
},
"denial_reason": {
"description": "medical_necessity | prior_auth | out_of_network | experimental | coding_error",
"type": "string"
},
"diagnosis": {
"maxLength": 200,
"type": "string"
},
"insurer": {
"type": "string"
},
"state": {
"maxLength": 2,
"type": "string"
}
},
"required": [
"insurer",
"denial_reason",
"cpt_code"
],
"type": "object"
},
"name": "estimate_appeal_success",
"outputSchema": null
},
{
"description": "[Taxonomy VII.124 — baseline response (public data only)] Generate an evidence package supporting a claim or appeal (references, studies, policies).\n\nWHEN TO USE: User has a denied claim and wants to appeal, or is preparing arguments / evidence / escalation steps for one.\n\nWHEN NOT: For explaining what a denial code means without drafting an appeal, use denial_code_explainer first. For finding a negotiation path on a non-denied bill, use negotiate_bill_script.",
"inputSchema": {
"additionalProperties": true,
"properties": {},
"type": "object"
},
"name": "evidence_pack_generator",
"outputSchema": null
},
{
"description": "Human-readable rationale for an appeal probability. Returns {probability, tier, recommended_posture, rationale, expected_days_to_resolution, tracking_id} grounded in aggregate outcome rates — not model feature weights. Use this when the caller wants 'why' in plain English alongside the number.\n\nWHEN TO USE: Reference lookups: individual code details, verifying a provider registry entry, checking a prior Medigami response's signature, or tracking an outcome.\n\nWHEN NOT: For composite workflows use the higher-level tool that calls these internally.",
"inputSchema": {
"properties": {
"amount": {
"type": "number"
},
"cpt_code": {
"type": "string"
},
"denial_reason": {
"type": "string"
},
"diagnosis": {
"maxLength": 200,
"type": "string"
},
"insurer": {
"type": "string"
},
"state": {
"type": "string"
}
},
"required": [
"insurer",
"denial_reason",
"cpt_code"
],
"type": "object"
},
"name": "explain_appeal_success",
"outputSchema": null
},
{
"description": "[Taxonomy B.8 — delegates to benchmark_payer_rate] Fair-market price distribution for a service: DP-noised percentiles (p10, p25, p50, p75, p90) for the given CPT in a ZIP3 region.\n\nWHEN TO USE: User wants to understand what a service typically costs, compare prices across regions/providers, or gauge whether a billed amount is reasonable.\n\nWHEN NOT: For a specific bill they have in hand, scan_bill_for_errors is more actionable. For insurance-path estimates, use deductible_impact_calculator or coinsurance_simulator.",
"inputSchema": {
"properties": {
"cpt_code": {
"type": "string"
},
"insurer": {
"description": "Optional insurer for payer-specific distribution.",
"type": "string"
},
"zip3": {
"description": "First 3 digits of ZIP.",
"type": "string"
}
},
"required": [
"cpt_code",
"zip3"
],
"type": "object"
},
"name": "fair_price_estimator",
"outputSchema": null
},
{
"description": "[Taxonomy X.181 — baseline response (public data only)] Find applicable financial-assistance programs (hospital charity, 340B, state, pharma).\n\nWHEN TO USE: User needs help paying a medical bill. Pass household_income_usd and family_size for FPL-based eligibility flags across 6 programs (501(r) charity, Medicaid, PE, manufacturer PAPs, 340B, state pools).\n\nWHEN NOT: For insured users with low exposure (use coinsurance_simulator or deductible_impact_calculator).\n\nEXAMPLES:\n- Find assistance for family of 3 at $45K income: `{\"household_income_usd\":45000,\"family_size\":3}`",
"inputSchema": {
"properties": {
"family_size": {
"description": "Number of people in the household. Used to compute FPL threshold.",
"minimum": 1,
"type": "integer"
},
"household_income_usd": {
"description": "Annual household income in USD. When provided, tool computes FPL ratio and flags likely-eligible programs.",
"type": "number"
}
},
"type": "object"
},
"name": "financial_assistance_finder",
"outputSchema": null
},
{
"description": "[Taxonomy X.176 — delegates to financial_risk_exposure_model] Model a member's financial exposure. Alias of financial_risk_exposure_model.\n\nWHEN TO USE: User is planning for a medical expense, comparing plan options, looking for financial assistance, or trying to structure a payment plan.\n\nWHEN NOT: For billing-error analysis (scan_bill_for_errors) or appeal drafting (generate_appeal_letter).",
"inputSchema": {
"additionalProperties": true,
"properties": {},
"type": "object"
},
"name": "financial_exposure_model",
"outputSchema": null
},
{
"description": "[Taxonomy H.42 — baseline response (public data only)] Quantify a patient's financial exposure to medical-debt risk given current plan, health status, and historical claim volatility.\n\nWHEN TO USE: User is planning for a medical expense, comparing plan options, looking for financial assistance, or trying to structure a payment plan.\n\nWHEN NOT: For billing-error analysis (scan_bill_for_errors) or appeal drafting (generate_appeal_letter).",
"inputSchema": {
"properties": {
"chronic_conditions": {
"items": {
"type": "string"
},
"type": "array"
},
"emergency_savings": {
"type": "number"
},
"household_income": {
"type": "number"
},
"plan_id": {
"type": "string"
}
},
"required": [
"plan_id"
],
"type": "object"
},
"name": "financial_risk_exposure_model",
"outputSchema": null
},
{
"description": "Format an LLM-citable reference to a previously-attested Medigami MCP response. Input: either the full signed envelope that an earlier attested tool returned, OR just a tracking_id. Returns a short citation string, a public verification URL a third party can open to inspect and cryptographically verify the payload, and a long-form attribution block. Use this after any substantive Medigami tool call (scan, estimate, resolve, benchmark) so the user has a verifiable reference to the specific answer and its expiration date.\n\nWHEN TO USE: After a substantive tool call, generate a citable string + short URL the LLM can paste into its user-facing response for later verification.\n\nWHEN NOT: For non-substantive lookups where citation is unnecessary.\n\nEXAMPLES:\n- Generate a citable URL from a tracking_id: `{\"tracking_id\":\"evt_abc123\"}`",
"inputSchema": {
"properties": {
"envelope": {
"description": "Full signed envelope returned by an attested Medigami tool (preferred).",
"type": "object"
},
"format": {
"description": "short = one-line citation string; long = paragraph attribution; both = return both (default).",
"enum": [
"short",
"long",
"both"
],
"type": "string"
},
"tracking_id": {
"description": "tracking_id alone; the resulting URL will still render but the third party must paste the envelope into the verifier form.",
"maxLength": 32,
"type": "string"
}
},
"required": [],
"type": "object"
},
"name": "format_citation",
"outputSchema": null
},
{
"description": "DEPRECATED ALIAS of format_citation — kept for backward compatibility with v0.1.7 clients. New code should call format_citation directly.\n\nWHEN TO USE: Reference lookups: individual code details, verifying a provider registry entry, checking a prior Medigami response's signature, or tracking an outcome.\n\nWHEN NOT: For composite workflows use the higher-level tool that calls these internally.",
"inputSchema": {
"properties": {
"envelope": {
"description": "Full signed envelope returned by an attested Medigami tool (preferred).",
"type": "object"
},
"format": {
"description": "short = one-line citation string; long = paragraph attribution; both = return both (default).",
"enum": [
"short",
"long",
"both"
],
"type": "string"
},
"tracking_id": {
"description": "tracking_id alone; the resulting URL will still render but the third party must paste the envelope into the verifier form.",
"maxLength": 32,
"type": "string"
}
},
"required": [],
"type": "object"
},
"name": "format_medigami_citation",
"outputSchema": null
},
{
"description": "Generate a legally-grounded insurance appeal letter for a denied claim. Returns the letter as a template with [PATIENT NAME] and [PROVIDER NAME] placeholders (structured-only PHI posture). Includes legal citations, recommended attachments, and appeal-deadline calendar.\n\nWHEN TO USE: User has a specific claim denied and wants a drafted appeal letter. Requires insurer, denial_reason (CARC code), cpt_code, diagnosis (ICD-10), and dollar amount. Returns an attested letter with reversal rate, insurer-specific tips, recommended attachments.\n\nWHEN NOT: If the user only wants to understand a denial code, use denial_code_explainer first. If they haven't received a formal denial yet, don't draft — clarify status first. For non-CARC disputes (e.g. billing errors pre-adjudication), use scan_bill_for_errors.\n\nEXAMPLES:\n- Draft CO-16 appeal to UHC for office visit: `{\"insurer\":\"UnitedHealthcare\",\"d...",
"inputSchema": {
"properties": {
"amount": {
"description": "Dollar amount in dispute (number, no currency symbol).",
"type": "number"
},
"cpt_code": {
"description": "Single CPT/HCPCS code, e.g. '99213' or 'J0585'.",
"maxLength": 10,
"type": "string"
},
"denial_reason": {
"description": "CARC/RARC denial code, e.g. 'CO-16' or 'CO-97'. Code only — do NOT include the human-readable expansion of the code.",
"maxLength": 50,
"type": "string"
},
"diagnosis": {
"description": "Single ICD-10 code, e.g. 'I10' or 'E11.9'.",
"maxLength": 20,
"type": "string"
},
"insurer": {
"description": "Insurer canonical name, e.g. 'UnitedHealthcare', 'Aetna'.",
"maxLength": 100,
"type": "string"
},
"state": {
"description": "Two-letter US state code for state-specific disclaimers.",
"maxLength": 2,
"type": "string"
}
},
"required": [
"insurer",
"denial_reason",
"cpt_code",
"diagnosis",
"amount"
],
"type": "object"
},
"name": "generate_appeal_letter",
"outputSchema": null
},
{
"description": "[Taxonomy F.28 — delegates to generate_appeal_letter] [Taxonomy alias] Generate a state-specific insurance appeal letter with UPL-safe disclaimers for 19 US states. Same impl as generate_appeal_letter.\n\nWHEN TO USE: User has a denied claim and wants to appeal, or is preparing arguments / evidence / escalation steps for one.\n\nWHEN NOT: For explaining what a denial code means without drafting an appeal, use denial_code_explainer first. For finding a negotiation path on a non-denied bill, use negotiate_bill_script.",
"inputSchema": {
"properties": {
"amount": {
"type": "number"
},
"cpt_code": {
"type": "string"
},
"denial_reason": {
"type": "string"
},
"diagnosis": {
"type": "string"
},
"insurer": {
"type": "string"
},
"state": {
"type": "string"
}
},
"required": [
"insurer",
"denial_reason",
"cpt_code",
"diagnosis",
"amount"
],
"type": "object"
},
"name": "generate_appeal_letter_v2",
"outputSchema": null
},
{
"description": "External-review filing deadline for a state + the date of the FINAL adverse determination. Returns the deadline date, the statutory window label + citation, and whether the exact state-specific window still needs verification (most states carry a conservative NAIC-model 4-month floor unless statute-confirmed, e.g. CA/NY). Free, no auth.\n\nWHEN TO USE: Reference lookups: individual code details, verifying a provider registry entry, checking a prior Medigami response's signature, or tracking an outcome.\n\nWHEN NOT: For composite workflows use the higher-level tool that calls these internally.",
"inputSchema": {
"properties": {
"denial_date": {
"description": "ISO date (YYYY-MM-DD) of the FINAL adverse determination",
"maxLength": 10,
"type": "string"
},
"state": {
"description": "2-letter US state",
"maxLength": 2,
"type": "string"
}
},
"required": [
"denial_date"
],
"type": "object"
},
"name": "get_appeal_deadline",
"outputSchema": null
},
{
"description": "Where and how to file an external review for a given state — the venue name, filing channel (portal/mail/fax), portal URL, and whether expedited review is available. Free, no auth.\n\nWHEN TO USE: Reference lookups: individual code details, verifying a provider registry entry, checking a prior Medigami response's signature, or tracking an outcome.\n\nWHEN NOT: For composite workflows use the higher-level tool that calls these internally.",
"inputSchema": {
"properties": {
"state": {
"description": "2-letter US state",
"maxLength": 2,
"type": "string"
}
},
"type": "object"
},
"name": "get_venue",
"outputSchema": null
},
{
"description": "[Taxonomy X.183 — baseline response (public data only)] Forecast a household's annual healthcare spend based on plan + utilization.\n\nWHEN TO USE: User planning annual healthcare spend, comparing plans, or estimating worst-case exposure.\n\nWHEN NOT: For a specific procedure cost (benchmark_payer_rate).\n\nEXAMPLES:\n- Forecast annual spend range: `{}`",
"inputSchema": {
"properties": {
"plan_deductible_usd": {
"type": "number"
},
"plan_oop_max_usd": {
"type": "number"
}
},
"type": "object"
},
"name": "healthcare_budget_forecaster",
"outputSchema": null
},
{
"description": "[Taxonomy II.22 — baseline response (public data only)] For a given ICD-10, surface the CPT codes typically billed for that diagnosis.\n\nWHEN TO USE: User has an ICD-10 diagnosis and wants to know what CPTs are commonly billed for it.\n\nWHEN NOT: For planning specific services (use benchmark_payer_rate once the CPT is chosen).\n\nEXAMPLES:\n- Common CPTs for essential hypertension: `{\"icd10_code\":\"I10\"}`",
"inputSchema": {
"properties": {
"icd10_code": {
"description": "Single ICD-10-CM code, e.g. 'I10'. Returns common CPT candidates.",
"type": "string"
}
},
"required": [
"icd10_code"
],
"type": "object"
},
"name": "icd_to_cpt_mapper",
"outputSchema": null
},
{
"description": "[Taxonomy III.46 — baseline response (public data only)] Inflation-adjusted price comparison across years for a CPT.\n\nWHEN TO USE: User has a historical dollar amount and wants it adjusted for medical-care inflation to a given year.\n\nWHEN NOT: For current market prices (benchmark_payer_rate).\n\nEXAMPLES:\n- Adjust $1K 3yr forward at medical CPI: `{\"base_amount_usd\":1000,\"years\":3}`",
"inputSchema": {
"properties": {
"base_amount_usd": {
"type": "number"
},
"years": {
"maximum": 50,
"minimum": 0,
"type": "number"
}
},
"required": [
"base_amount_usd",
"years"
],
"type": "object"
},
"name": "inflation_adjusted_price_model",
"outputSchema": null
},
{
"description": "[Taxonomy H.39 — baseline response (public data only)] Given a patient's historical claim patterns, rank available insurance plans by expected annual cost.\n\nWHEN TO USE: User is planning for a medical expense, comparing plan options, looking for financial assistance, or trying to structure a payment plan.\n\nWHEN NOT: For billing-error analysis (scan_bill_for_errors) or appeal drafting (generate_appeal_letter).",
"inputSchema": {
"properties": {
"chronic_conditions": {
"items": {
"type": "string"
},
"type": "array"
},
"historical_spend": {
"description": "Prior-year OOP spend.",
"type": "number"
},
"household_size": {
"type": "integer"
},
"income_band": {
"type": "string"
},
"zip_code": {
"type": "string"
}
},
"required": [
"zip_code"
],
"type": "object"
},
"name": "insurance_plan_optimizer",
"outputSchema": null
},
{
"description": "[Taxonomy F.31 — baseline response (public data only)] Parse an insurer's response letter or EOB into structured fields: denial reason codes, appeal rights, deadlines, next-step recommendations.\n\nWHEN TO USE: User has a denied claim and wants to appeal, or is preparing arguments / evidence / escalation steps for one.\n\nWHEN NOT: For explaining what a denial code means without drafting an appeal, use denial_code_explainer first. For finding a negotiation path on a non-denied bill, use negotiate_bill_script.",
"inputSchema": {
"properties": {
"response_text": {
"description": "Insurer response or EOB text.",
"type": "string"
},
"response_type": {
"enum": [
"denial",
"partial_denial",
"eob",
"appeal_response"
],
"type": "string"
}
},
"required": [
"response_text"
],
"type": "object"
},
"name": "insurance_response_interpreter",
"outputSchema": null
},
{
"description": "[Taxonomy X.185 — baseline response (public data only)] Recommend insurance-plan selections to maximize value given projected utilization.\n\nWHEN TO USE: User is planning for a medical expense, comparing plan options, looking for financial assistance, or trying to structure a payment plan.\n\nWHEN NOT: For billing-error analysis (scan_bill_for_errors) or appeal drafting (generate_appeal_letter).",
"inputSchema": {
"additionalProperties": true,
"properties": {},
"type": "object"
},
"name": "insurance_value_optimizer",
"outputSchema": null
},
{
"description": "Look up a CPT or HCPCS-J code or search by keyword. Covers the most common outpatient billing codes (E/M, preventive, lab, imaging, procedure, cardiology, therapy, behavioral, vaccine, injectable drugs). Note: CPT is a registered trademark of the American Medical Association; full-dataset commercial use requires an AMA license. This tool provides short descriptors for identification in billing-review workflows.\n\nWHEN TO USE: User asks about a specific CPT/HCPCS procedure code or wants to search for codes by procedure description.\n\nWHEN NOT: For the expected ICD pairings (icd_to_cpt_mapper or cpt_to_icd_mapper).\n\nEXAMPLES:\n- Find CPT for routine office visit: `{\"query\":\"office visit established patient\"}`",
"inputSchema": {
"properties": {
"query": {
"description": "CPT / HCPCS-J code ('99213', 'J1885') or keyword ('knee MRI', 'colonoscopy').",
"maxLength": 200,
"type": "string"
}
},
"required": [
"query"
],
"type": "object"
},
"name": "lookup_cpt",
"outputSchema": null
},
{
"description": "Look up an ICD-10-CM diagnosis code or search by keyword. Input is either an exact code (e.g. 'E11.21') or a free-text description phrase ('type 2 diabetes with nephropathy'). Returns either the matching code + description or up to 20 candidate matches. Use when a clinical note uses non-standard phrasing and the correct code is needed for billing.\n\nWHEN TO USE: User asks about a specific ICD-10 diagnosis code or wants RAG-search over ICD-10 for a condition name.\n\nWHEN NOT: For the matching CPT codes (cpt_to_icd_mapper). For code validation against a payer (code_validation).\n\nEXAMPLES:\n- Find ICD-10 for hypertension: `{\"query\":\"essential hypertension\"}`",
"inputSchema": {
"properties": {
"query": {
"description": "ICD-10-CM code (e.g. 'I10', 'E11.21') or keyword search.",
"maxLength": 200,
"type": "string"
}
},
"required": [
"query"
],
"type": "object"
},
"name": "lookup_icd10",
"outputSchema": null
},
{
"description": "Look up a provider in the CMS NPPES National Provider Identifier registry. Accepts a 10-digit NPI number OR a provider name (optionally narrowed by 2-char state). Returns up to 20 matches with entity type, specialty, taxonomy code, address, and status. Source: CMS NPPES public API (free, no key required).\n\nWHEN TO USE: User wants to verify a specific provider by NPI number, or find a provider by name + state.\n\nWHEN NOT: For provider performance analytics (provider_efficiency_score).\n\nEXAMPLES:\n- Look up a provider by NPI number: `{\"npi_number\":\"1234567893\"}`",
"inputSchema": {
"properties": {
"query": {
"description": "10-digit NPI (e.g. '1234567890') or provider name ('Jane Smith').",
"maxLength": 200,
"type": "string"
},
"state": {
"description": "Optional 2-char state abbreviation to narrow a name search.",
"maxLength": 2,
"type": "string"
}
},
"required": [
"query"
],
"type": "object"
},
"name": "lookup_npi",
"outputSchema": null
},
{
"description": "Look up a NUCC provider taxonomy code (the specialty codes used on HIPAA transactions + NPI registrations) or search by keyword. Returns classification + type + optional specialization. Source: NUCC Health Care Provider Taxonomy Code Set (public; CMS-accepted).\n\nWHEN TO USE: Resolving a NUCC provider taxonomy code to its specialty description.\n\nWHEN NOT: For finding a provider by specialty in a region (not yet implemented).",
"inputSchema": {
"properties": {
"query": {
"description": "Taxonomy code ('207Q00000X') or keyword ('cardiology', 'pediatrics').",
"maxLength": 200,
"type": "string"
}
},
"required": [
"query"
],
"type": "object"
},
"name": "lookup_provider_taxonomy",
"outputSchema": null
},
{
"description": "[Taxonomy III.55 — baseline response (public data only)] Full DP-noised market price distribution for a CPT+region pair.\n\nWHEN TO USE: User wants to understand what a service typically costs, compare prices across regions/providers, or gauge whether a billed amount is reasonable.\n\nWHEN NOT: For a specific bill they have in hand, scan_bill_for_errors is more actionable. For insurance-path estimates, use deductible_impact_calculator or coinsurance_simulator.",
"inputSchema": {
"additionalProperties": true,
"properties": {},
"type": "object"
},
"name": "market_price_distribution_model",
"outputSchema": null
},
{
"description": "Given a prior scan_id, returns a prioritized action list: anomalies ranked by (expected overcharge x recovery probability), with the next steps to pursue each. Use after scan_bill_for_errors.\n\nWHEN TO USE: User has already run scan_bill_for_errors and wants the anomalies ranked by expected dollar recovery.\n\nWHEN NOT: As a first call — always scan first.",
"inputSchema": {
"properties": {
"scan_id": {
"type": "string"
}
},
"required": [
"scan_id"
],
"type": "object"
},
"name": "maximize_recovery",
"outputSchema": null
},
{
"description": "[Taxonomy X.184 — baseline response (public data only)] Analyze a patient's medical spending over a period and surface optimization opportunities.\n\nWHEN TO USE: User is planning for a medical expense, comparing plan options, looking for financial assistance, or trying to structure a payment plan.\n\nWHEN NOT: For billing-error analysis (scan_bill_for_errors) or appeal drafting (generate_appeal_letter).",
"inputSchema": {
"additionalProperties": true,
"properties": {},
"type": "object"
},
"name": "medical_spending_analyzer",
"outputSchema": null
},
{
"description": "Federal appeal-deadline window (ERISA §503 internal-appeal / ACA §2719 external-review / NSA IDR) for a plan type. Public regulator data, k-anonymity floored, not legal advice.\n\nWHEN TO USE: Reference lookups: individual code details, verifying a provider registry entry, checking a prior Medigami response's signature, or tracking an outcome.\n\nWHEN NOT: For composite workflows use the higher-level tool that calls these internally.",
"inputSchema": {
"properties": {
"plan_type": {
"description": "e.g. 'self_funded', 'aca_marketplace', 'medicare', 'medicaid'.",
"maxLength": 40,
"type": "string"
},
"state": {
"description": "2-letter US state (echoed on the row; the deadline window itself is federal, not state-varying).",
"maxLength": 32,
"type": "string"
}
},
"required": [
"state",
"plan_type"
],
"type": "object"
},
"name": "medigami_deadline",
"outputSchema": {
"additionalProperties": true,
"properties": {
"as_of": {
"type": [
"string",
"null"
]
},
"basis": {
"type": [
"string",
"null"
]
},
"command": {
"type": "string"
},
"cta": {
"type": "object"
},
"permalink": {
"type": [
"string",
"null"
]
},
"refused": {
"type": "string"
},
"result_kind": {
"type": "string"
},
"rows": {
"type": "array"
},
"source_url": {
"type": "string"
},
"unresolved": {
"type": "array"
}
},
"required": [
"command",
"permalink",
"source_url"
],
"type": "object"
}
},
{
"description": "Historical external-review overturn rate published by the state regulator for the insurer you name, in a regulated venue (CA/NY/MD/NJ/MI/OH/NC). Returns one insurer's own rate — not a comparison or ranking against other insurers. Public regulator data, k-anonymity floored, not legal advice.\n\nWHEN TO USE: Reference lookups: individual code details, verifying a provider registry entry, checking a prior Medigami response's signature, or tracking an outcome.\n\nWHEN NOT: For composite workflows use the higher-level tool that calls these internally.",
"inputSchema": {
"properties": {
"insurer": {
"description": "Insurer / payer name.",
"maxLength": 100,
"type": "string"
},
"state": {
"description": "Venue state, e.g. 'CA', 'NY'.",
"maxLength": 32,
"type": "string"
}
},
"required": [
"insurer",
"state"
],
"type": "object"
},
"name": "medigami_odds",
"outputSchema": {
"additionalProperties": true,
"properties": {
"as_of": {
"type": [
"string",
"null"
]
},
"basis": {
"type": [
"string",
"null"
]
},
"command": {
"type": "string"
},
"cta": {
"type": "object"
},
"permalink": {
"type": [
"string",
"null"
]
},
"refused": {
"type": "string"
},
"result_kind": {
"type": "string"
},
"rows": {
"type": "array"
},
"source_url": {
"type": "string"
},
"unresolved": {
"type": "array"
}
},
"required": [
"command",
"permalink",
"source_url"
],
"type": "object"
}
},
{
"description": "A hospital's own MRF-published negotiated rate for a CPT code (no billed-amount comparison — use medigami_roast for that). Public regulator data, k-anonymity floored, not legal advice.\n\nWHEN TO USE: Reference lookups: individual code details, verifying a provider registry entry, checking a prior Medigami response's signature, or tracking an outcome.\n\nWHEN NOT: For composite workflows use the higher-level tool that calls these internally.",
"inputSchema": {
"properties": {
"cpt": {
"description": "CPT/HCPCS procedure code.",
"maxLength": 10,
"type": "string"
},
"hospital": {
"description": "Hospital / facility name.",
"maxLength": 200,
"type": "string"
}
},
"required": [
"hospital",
"cpt"
],
"type": "object"
},
"name": "medigami_rate",
"outputSchema": {
"additionalProperties": true,
"properties": {
"as_of": {
"type": [
"string",
"null"
]
},
"basis": {
"type": [
"string",
"null"
]
},
"command": {
"type": "string"
},
"cta": {
"type": "object"
},
"permalink": {
"type": [
"string",
"null"
]
},
"refused": {
"type": "string"
},
"result_kind": {
"type": "string"
},
"rows": {
"type": "array"
},
"source_url": {
"type": "string"
},
"unresolved": {
"type": "array"
}
},
"required": [
"command",
"permalink",
"source_url"
],
"type": "object"
}
},
{
"description": "Compare a billed charge against a hospital's own MRF-published negotiated rate for a CPT code; returns the markup multiple. Public regulator data, k-anonymity floored, not legal advice.\n\nWHEN TO USE: Reference lookups: individual code details, verifying a provider registry entry, checking a prior Medigami response's signature, or tracking an outcome.\n\nWHEN NOT: For composite workflows use the higher-level tool that calls these internally.",
"inputSchema": {
"properties": {
"billed_amount": {
"description": "Amount billed, USD.",
"minimum": 0,
"type": "number"
},
"cpt": {
"description": "CPT/HCPCS procedure code.",
"maxLength": 10,
"type": "string"
},
"hospital": {
"description": "Hospital / facility name.",
"maxLength": 200,
"type": "string"
}
},
"required": [
"hospital",
"cpt",
"billed_amount"
],
"type": "object"
},
"name": "medigami_roast",
"outputSchema": {
"additionalProperties": true,
"properties": {
"as_of": {
"type": [
"string",
"null"
]
},
"basis": {
"type": [
"string",
"null"
]
},
"command": {
"type": "string"
},
"cta": {
"type": "object"
},
"permalink": {
"type": [
"string",
"null"
]
},
"refused": {
"type": "string"
},
"result_kind": {
"type": "string"
},
"rows": {
"type": "array"
},
"source_url": {
"type": "string"
},
"unresolved": {
"type": "array"
}
},
"required": [
"command",
"permalink",
"source_url"
],
"type": "object"
}
},
{
"description": "Generate a phone script the user can read when negotiating a medical bill directly with the provider. Combines DP-noised commercial rate benchmarks + the caller's household income + federal charity-care rules (IRS §501(r)) into three negotiation angles: financial assistance, self-pay discount, and itemized-bill coding review. Returns the script + reference-only benchmark range (for the user's own research, not an insurance-consulting recommendation) + charity-care tier. Output is educational only; the user negotiates on their own behalf. Some states (notably NY, FL, CA) regulate public-adjuster activity — the attached disclaimer references this.\n\nWHEN TO USE: User wants talking points and a target settlement range to negotiate a medical bill with the provider. Best for self-pay and out-of-network balances.\n\nWHEN NOT: For a bill that was denied (generate_appeal_letter — the payer, not ...",
"inputSchema": {
"properties": {
"billed_amount": {
"minimum": 1,
"type": "number"
},
"cpt_code": {
"type": "string"
},
"household_income_annual": {
"minimum": 0,
"type": "number"
},
"household_size": {
"maximum": 20,
"minimum": 1,
"type": "integer"
},
"insurer": {
"type": "string"
},
"state": {
"type": "string"
},
"zip3": {
"type": "string"
}
},
"required": [
"cpt_code",
"billed_amount"
],
"type": "object"
},
"name": "negotiate_bill_script",
"outputSchema": null
},
{
"description": "[Taxonomy F.30 — baseline response (public data only)] Given a bill + patient situation, generate a ranked negotiation strategy: hardship appeal, charity-care application, itemization request, phone scripts.\n\nWHEN TO USE: User has a denied claim and wants to appeal, or is preparing arguments / evidence / escalation steps for one.\n\nWHEN NOT: For explaining what a denial code means without drafting an appeal, use denial_code_explainer first. For finding a negotiation path on a non-denied bill, use negotiate_bill_script.",
"inputSchema": {
"properties": {
"bill_amount": {
"type": "number"
},
"insurance_status": {
"type": "string"
},
"provider": {
"type": "string"
},
"situation": {
"enum": [
"uninsured",
"underinsured",
"hardship",
"dispute"
],
"type": "string"
}
},
"required": [
"bill_amount"
],
"type": "object"
},
"name": "negotiation_strategy_generator",
"outputSchema": null
},
{
"description": "Find the lowest-cost path for a prescription: generics, biosimilars, GoodRx coupons, manufacturer assistance, 90-day fills, and mail-order vs retail comparison. Returns ranked options with annual savings vs current copay.\n\nWHEN TO USE: User asks about prescription cost — lowest-price generic, biosimilar, GoodRx coupon, mail-order, manufacturer assistance, or 90-day fill options.\n\nWHEN NOT: For insurance-covered Rx copay questions (use copay_model). For medical necessity appeals of formulary denials (use generate_appeal_letter).\n\nEXAMPLES:\n- Find cheapest path for atorvastatin 20mg: `{\"drug_name\":\"atorvastatin 20mg\",\"current_insurance_cost_30day\":45,\"is_maintenance_med\":true}`",
"inputSchema": {
"properties": {
"current_insurance_cost_30day": {
"type": "number"
},
"drug_name": {
"type": "string"
},
"is_maintenance_med": {
"type": "boolean"
},
"ndc_code": {
"type": "string"
},
"zip_code": {
"type": "string"
}
},
"required": [
"drug_name"
],
"type": "object"
},
"name": "optimize_prescription",
"outputSchema": null
},
{
"description": "[Taxonomy X.174 — baseline response (public data only)] Optimize out-of-pocket spend across a sequence of planned services.\n\nWHEN TO USE: User is planning for a medical expense, comparing plan options, looking for financial assistance, or trying to structure a payment plan.\n\nWHEN NOT: For billing-error analysis (scan_bill_for_errors) or appeal drafting (generate_appeal_letter).",
"inputSchema": {
"additionalProperties": true,
"properties": {},
"type": "object"
},
"name": "out_of_pocket_optimizer",
"outputSchema": null
},
{
"description": "[Taxonomy III.53 — baseline response (public data only)] Flag services billed materially above market percentile thresholds.\n\nWHEN TO USE: User wants to understand what a service typically costs, compare prices across regions/providers, or gauge whether a billed amount is reasonable.\n\nWHEN NOT: For a specific bill they have in hand, scan_bill_for_errors is more actionable. For insurance-path estimates, use deductible_impact_calculator or coinsurance_simulator.",
"inputSchema": {
"additionalProperties": true,
"properties": {},
"type": "object"
},
"name": "overpriced_service_detector",
"outputSchema": null
},
{
"description": "[Taxonomy X.182 — baseline response (public data only)] Explain why a specific charge appears on a bill in plain language.\n\nWHEN TO USE: User is planning for a medical expense, comparing plan options, looking for financial assistance, or trying to structure a payment plan.\n\nWHEN NOT: For billing-error analysis (scan_bill_for_errors) or appeal drafting (generate_appeal_letter).",
"inputSchema": {
"additionalProperties": true,
"properties": {},
"type": "object"
},
"name": "patient_cost_explainer",
"outputSchema": null
},
{
"description": "[Taxonomy H.38 — baseline response (public data only)] Given a patient's plan + predicted care needs, forecast annual out-of-pocket spend across expected claims.\n\nWHEN TO USE: User is planning for a medical expense, comparing plan options, looking for financial assistance, or trying to structure a payment plan.\n\nWHEN NOT: For billing-error analysis (scan_bill_for_errors) or appeal drafting (generate_appeal_letter).",
"inputSchema": {
"properties": {
"chronic_conditions": {
"description": "ICD-10 codes for chronic care.",
"items": {
"type": "string"
},
"type": "array"
},
"expected_procedures": {
"description": "CPT codes expected this year.",
"items": {
"type": "string"
},
"type": "array"
},
"plan_id": {
"type": "string"
}
},
"required": [
"plan_id"
],
"type": "object"
},
"name": "patient_cost_forecaster",
"outputSchema": null
},
{
"description": "[Taxonomy X.186 — baseline response (public data only)] Score a patient's financial risk exposure from planned or ongoing care.\n\nWHEN TO USE: User is planning for a medical expense, comparing plan options, looking for financial assistance, or trying to structure a payment plan.\n\nWHEN NOT: For billing-error analysis (scan_bill_for_errors) or appeal drafting (generate_appeal_letter).",
"inputSchema": {
"additionalProperties": true,
"properties": {},
"type": "object"
},
"name": "patient_financial_risk_score",
"outputSchema": null
},
{
"description": "[Taxonomy VII.130 — baseline response (public data only)] Return payer-specific appeal templates known to perform well.\n\nWHEN TO USE: User has a denied claim and wants to appeal, or is preparing arguments / evidence / escalation steps for one.\n\nWHEN NOT: For explaining what a denial code means without drafting an appeal, use denial_code_explainer first. For finding a negotiation path on a non-denied bill, use negotiate_bill_script.",
"inputSchema": {
"additionalProperties": true,
"properties": {},
"type": "object"
},
"name": "payer_specific_appeal_templates",
"outputSchema": null
},
{
"description": "[Taxonomy X.180 — baseline response (public data only)] Optimize a payment plan structure for a patient balance.\n\nWHEN TO USE: User has a balance and wants to structure a payment plan. Pass balance_usd and months.\n\nWHEN NOT: If user may qualify for charity care — run financial_assistance_finder first.\n\nEXAMPLES:\n- 12-month plan for $3K balance: `{\"balance_usd\":3000,\"months\":12}`",
"inputSchema": {
"properties": {
"balance_usd": {
"type": "number"
},
"months": {
"maximum": 120,
"minimum": 1,
"type": "integer"
}
},
"required": [
"balance_usd"
],
"type": "object"
},
"name": "payment_plan_optimizer",
"outputSchema": null
},
{
"description": "[Taxonomy III.52 — baseline response (public data only)] Detect service-line prices statistically anomalous versus market.\n\nWHEN TO USE: User wants to understand what a service typically costs, compare prices across regions/providers, or gauge whether a billed amount is reasonable.\n\nWHEN NOT: For a specific bill they have in hand, scan_bill_for_errors is more actionable. For insurance-path estimates, use deductible_impact_calculator or coinsurance_simulator.",
"inputSchema": {
"additionalProperties": true,
"properties": {},
"type": "object"
},
"name": "price_anomaly_detector",
"outputSchema": null
},
{
"description": "[Taxonomy III.56 — baseline response (public data only)] Detect claim-line outliers relative to a learned market distribution.\n\nWHEN TO USE: User wants to understand what a service typically costs, compare prices across regions/providers, or gauge whether a billed amount is reasonable.\n\nWHEN NOT: For a specific bill they have in hand, scan_bill_for_errors is more actionable. For insurance-path estimates, use deductible_impact_calculator or coinsurance_simulator.",
"inputSchema": {
"additionalProperties": true,
"properties": {},
"type": "object"
},
"name": "price_outlier_detector",
"outputSchema": null
},
{
"description": "[Taxonomy III.58 — baseline response (public data only)] Recommend a reasonable price to propose to a provider for a service (self-pay or negotiation).\n\nWHEN TO USE: User wants to understand what a service typically costs, compare prices across regions/providers, or gauge whether a billed amount is reasonable.\n\nWHEN NOT: For a specific bill they have in hand, scan_bill_for_errors is more actionable. For insurance-path estimates, use deductible_impact_calculator or coinsurance_simulator.",
"inputSchema": {
"additionalProperties": true,
"properties": {},
"type": "object"
},
"name": "price_recommendation_engine",
"outputSchema": null
},
{
"description": "[Taxonomy B.9 — baseline response (public data only)] Given a target price and a CPT+region, return how many standard deviations above/below the market the target sits, plus confidence.\n\nWHEN TO USE: User wants to understand what a service typically costs, compare prices across regions/providers, or gauge whether a billed amount is reasonable.\n\nWHEN NOT: For a specific bill they have in hand, scan_bill_for_errors is more actionable. For insurance-path estimates, use deductible_impact_calculator or coinsurance_simulator.",
"inputSchema": {
"properties": {
"cpt_code": {
"type": "string"
},
"observed_price": {
"description": "Price to evaluate, USD.",
"type": "number"
},
"zip3": {
"type": "string"
}
},
"required": [
"cpt_code",
"observed_price",
"zip3"
],
"type": "object"
},
"name": "price_variance_analyzer",
"outputSchema": null
},
{
"description": "[Taxonomy X.177 — baseline response (public data only)] Rank a set of procedures by affordability for a given member.\n\nWHEN TO USE: User is planning for a medical expense, comparing plan options, looking for financial assistance, or trying to structure a payment plan.\n\nWHEN NOT: For billing-error analysis (scan_bill_for_errors) or appeal drafting (generate_appeal_letter).",
"inputSchema": {
"additionalProperties": true,
"properties": {},
"type": "object"
},
"name": "procedure_affordability_ranker",
"outputSchema": null
},
{
"description": "[Taxonomy III.57 — baseline response (public data only)] Decompose the cost of a procedure into component services + facility + professional fees.\n\nWHEN TO USE: User wants to understand what a service typically costs, compare prices across regions/providers, or gauge whether a billed amount is reasonable.\n\nWHEN NOT: For a specific bill they have in hand, scan_bill_for_errors is more actionable. For insurance-path estimates, use deductible_impact_calculator or coinsurance_simulator.",
"inputSchema": {
"additionalProperties": true,
"properties": {},
"type": "object"
},
"name": "procedure_cost_decomposition",
"outputSchema": null
},
{
"description": "[Taxonomy III.43 — baseline response (public data only)] Regional price benchmark for a CPT at state/metro/ZIP3 granularity.\n\nWHEN TO USE: User wants to understand what a service typically costs, compare prices across regions/providers, or gauge whether a billed amount is reasonable.\n\nWHEN NOT: For a specific bill they have in hand, scan_bill_for_errors is more actionable. For insurance-path estimates, use deductible_impact_calculator or coinsurance_simulator.",
"inputSchema": {
"additionalProperties": true,
"properties": {},
"type": "object"
},
"name": "regional_price_benchmark",
"outputSchema": null
},
{
"description": "[Taxonomy A.1 — baseline response (public data only)] Unified code resolver — free-form query or clinical description → ranked ICD-10-CM, CPT, and HCPCS codes with confidence scores. Use when you need to translate symptoms, procedures, or diagnoses into billable codes without running three separate lookups.\n\nWHEN TO USE: User asks about medical codes: what a CPT/ICD/HCPCS code means, whether a code combination is valid, or how to map between them.\n\nWHEN NOT: For full bill scans (use scan_bill_for_errors). For appealing a coding-related denial (use generate_appeal_letter).",
"inputSchema": {
"properties": {
"code_types": {
"description": "Optional filter — defaults to all three.",
"items": {
"enum": [
"icd10",
"cpt",
"hcpcs"
],
"type": "string"
},
"type": "array"
},
"max_results": {
"description": "Cap on ranked results. Default 5.",
"maximum": 20,
"minimum": 1,
"type": "integer"
},
"query": {
"description": "Free-form clinical description, symptom, or procedure.",
"type": "string"
}
},
"required": [
"query"
],
"type": "object"
},
"name": "resolve_codes",
"outputSchema": null
},
{
"description": "End-to-end denial resolution: returns appeal probability + confidence interval + a drafted letter template grounded in aggregate outcome data + plan-context flags (ERISA, restrictive-adjuster state). One call, one tracking_id. No recovery-financing product is offered by this tool.\n\nWHEN TO USE: Single-shot composite: user has a specific denial and wants scan + estimate + appeal + citation in one call.\n\nWHEN NOT: For nuanced step-by-step workflows, call the individual tools in order.\n\nEXAMPLES:\n- End-to-end CO-197 denial resolution: `{\"insurer\":\"Aetna\",\"denial_reason\":\"CO-197\",\"cpt_code\":\"45378\",\"state\":\"TX\",\"amount\":1850}`",
"inputSchema": {
"properties": {
"amount": {
"type": "number"
},
"cpt_code": {
"type": "string"
},
"denial_reason": {
"type": "string"
},
"diagnosis": {
"maxLength": 200,
"type": "string"
},
"insurer": {
"type": "string"
},
"plan_type_hint": {
"description": "self-funded | aca_marketplace | medicare | medicaid | ...",
"type": "string"
},
"state": {
"type": "string"
}
},
"required": [
"insurer",
"denial_reason",
"cpt_code"
],
"type": "object"
},
"name": "resolve_denial",
"outputSchema": null
},
{
"description": "Scan a medical bill or EOB text for errors: duplicate charges, CPT unbundling, upcoding, facility-fee overcharges. Returns flagged anomalies with estimated dollar impact and a total recovery estimate.\n\nPHI WARNING: bill text typically contains PHI (patient name, DOB, MRN, insurer ID). Medigami runs a server-side PHI redactor before any downstream LLM call when scan_bill is invoked from the public SKU, but best practice is to redact client-side before passing the bill through an LLM tool call. For your own bill only — this tool is not for reviewing someone else's claims.\n\nWHEN TO USE: User pastes or uploads a medical bill, EOB, itemized statement, hospital charge summary, or similar. The bill text can be raw (OCR output fine) — the scanner parses it. Prefer this over manual line-by-line analysis for any bill above ~$100.\n\nWHEN NOT: For a denial appeal (generate_appeal_letter). For pre-...",
"inputSchema": {
"properties": {
"bill_text": {
"description": "Bill/EOB text. Client-side redaction recommended.",
"maxLength": 50000,
"type": "string"
},
"insurer": {
"type": "string"
},
"provider": {
"type": "string"
},
"total": {
"type": "number"
},
"zip_code": {
"type": "string"
}
},
"required": [
"bill_text"
],
"type": "object"
},
"name": "scan_bill_for_errors",
"outputSchema": null
},
{
"description": "[Taxonomy F.32 — baseline response (public data only)] For a disputed bill, compute the optimal settlement target price balancing probability of acceptance against amount saved.\n\nWHEN TO USE: User has a denied claim and wants to appeal, or is preparing arguments / evidence / escalation steps for one.\n\nWHEN NOT: For explaining what a denial code means without drafting an appeal, use denial_code_explainer first. For finding a negotiation path on a non-denied bill, use negotiate_bill_script.",
"inputSchema": {
"properties": {
"bill_amount": {
"type": "number"
},
"dispute_leverage": {
"enum": [
"high",
"medium",
"low"
],
"type": "string"
},
"patient_ability_to_pay": {
"description": "Monthly discretionary income, USD.",
"type": "number"
},
"provider": {
"type": "string"
}
},
"required": [
"bill_amount"
],
"type": "object"
},
"name": "settlement_optimizer",
"outputSchema": null
},
{
"description": "[Taxonomy III.44 — baseline response (public data only)] Price benchmark for a CPT within a specific provider specialty.\n\nWHEN TO USE: User wants to understand what a service typically costs, compare prices across regions/providers, or gauge whether a billed amount is reasonable.\n\nWHEN NOT: For a specific bill they have in hand, scan_bill_for_errors is more actionable. For insurance-path estimates, use deductible_impact_calculator or coinsurance_simulator.",
"inputSchema": {
"additionalProperties": true,
"properties": {},
"type": "object"
},
"name": "specialty_price_benchmark",
"outputSchema": null
},
{
"description": "Submit a medical-claim denial letter to the Medigami Denial Common Crawl (public aggregate dataset). Consent-gated — caller must pass consent=true to attest the submission is voluntary. Server-side PHI scrubber runs before any storage; the public aggregate contains only coded fields (insurer_canonical, denial_reason_code, state, cpt_category, dollars_bin, days_to_resolution_bin). Raw text is never republished. Optional tracking_id closes the outcome loop to a prior Medigami scan / resolve call.\n\nWHEN TO USE: User wants to contribute a denial letter to the public Denial Common Crawl (consent-gated). PHI is scrubbed before aggregation.\n\nWHEN NOT: Just to explain a denial (denial_code_explainer). To draft a response (generate_appeal_letter).",
"inputSchema": {
"properties": {
"amount": {
"maximum": 10000000,
"minimum": 0,
"type": "number"
},
"consent": {
"description": "MUST be true — caller attests the submission is voluntary.",
"type": "boolean"
},
"cpt_code": {
"maxLength": 10,
"type": "string"
},
"days_to_resolution": {
"maximum": 3650,
"minimum": 0,
"type": "integer"
},
"letter_text": {
"description": "Raw denial-letter text. PHI scrubbed server-side.",
"maxLength": 40000,
"minLength": 40,
"type": "string"
},
"outcome_code": {
"description": "Optional: member_abandoned | appealed_won | appealed_lost | appealed_partial | pending",
"maxLength": 40,
"type": "string"
},
"state": {
"description": "2-char US state code or empty.",
"maxLength": 2,
"type": "string"
},
"tracking_id": {
"description": "Optional prior Medigami tracking_id to close the outcome loop.",
"maxLength": 32,
"type": "string"
}
},
"required": [
"letter_text",
"consent"
],
"type": "object"
},
"name": "submit_denial_letter",
"outputSchema": null
},
{
"description": "[Taxonomy VII.135 — baseline response (public data only)] Select optimal supporting documents for an appeal from an available document pool.\n\nWHEN TO USE: User is preparing an appeal and needs a ranked list of supporting documents for the denial category. Pass denial_code.\n\nWHEN NOT: Without denial_code — still returns generic docs but category-specific ranking is the high-value output.\n\nEXAMPLES:\n- Docs for a CO-50 medical-necessity denial: `{\"denial_code\":\"CO-50\"}`",
"inputSchema": {
"properties": {
"denial_code": {
"description": "CARC denial code, e.g. 'CO-50'. Drives category-specific document ranking.",
"type": "string"
},
"denial_reason": {
"description": "Alias for denial_code.",
"type": "string"
}
},
"type": "object"
},
"name": "supporting_document_selector",
"outputSchema": null
},
{
"description": "[Taxonomy X.178 — baseline response (public data only)] Compare expected costs across treatment alternatives for a condition.\n\nWHEN TO USE: User is planning for a medical expense, comparing plan options, looking for financial assistance, or trying to structure a payment plan.\n\nWHEN NOT: For billing-error analysis (scan_bill_for_errors) or appeal drafting (generate_appeal_letter).",
"inputSchema": {
"additionalProperties": true,
"properties": {},
"type": "object"
},
"name": "treatment_cost_comparator",
"outputSchema": null
},
{
"description": "[Taxonomy II.26 — delegates to scan_bill_for_errors] Detect CPT unbundling patterns in a claim. Alias of scan_bill_for_errors.\n\nWHEN TO USE: User asks about medical codes: what a CPT/ICD/HCPCS code means, whether a code combination is valid, or how to map between them.\n\nWHEN NOT: For full bill scans (use scan_bill_for_errors). For appealing a coding-related denial (use generate_appeal_letter).",
"inputSchema": {
"additionalProperties": true,
"properties": {},
"type": "object"
},
"name": "unbundling_detector",
"outputSchema": null
},
{
"description": "Verify an Ed25519-signed Medigami MCP response envelope — confirm a medical-bill / appeal / denial / rate answer came from Medigami and hasn't been tampered with. Input: the signed envelope + a public key (PEM) or expected-fingerprint you pinned out-of-band. Returns {valid, reason, tracking_id, timestamp, exp, public_key_fingerprint} so callers can cite the result as FRE 902(14) self-authenticating evidence.\n\nUsage:\n (a) Preferred: supply public_key_pem pinned out-of-band.\n (b) Otherwise: supply expected_fingerprint (SHA-256 of the pinned key); the envelope's embedded fingerprint is compared against it AND the key is fetched over HTTPS from the envelope's public_key_url (or Medigami's well-known URL) for signature verification. Freshness (exp) and fingerprint equality are both checked.\n\nNon-repudiation note: this tool deliberately does NOT silently fall back to the local server's ke...",
"inputSchema": {
"properties": {
"envelope": {
"description": "The signed response envelope",
"type": "object"
},
"expected_fingerprint": {
"description": "SHA-256 hex of the PEM public key you trust",
"type": "string"
},
"public_key_pem": {
"description": "PEM public key content (preferred)",
"type": "string"
}
},
"required": [
"envelope"
],
"type": "object"
},
"name": "verify_attestation",
"outputSchema": null
},
{
"description": "Validate the format + checksum of a DEA registration number (format: [A-Z][A-Z9][0-9]{7}; public checksum algorithm). Useful as a sanity check on a DEA number you were given (e.g. on a prescription label or a provider's letterhead). Scope note: this tool confirms the number is well-formed — it does NOT verify current registration status or the specific controlled-substance schedule the holder is authorized to prescribe. Authority verification requires a licensed DEA data broker (DEA ARCOS, RxMix).\n\nWHEN TO USE: Checking if a provider's DEA registration covers a specific controlled-substance CPT.\n\nWHEN NOT: For non-controlled-substance claims.",
"inputSchema": {
"properties": {
"cpt_code": {
"description": "Optional CPT context; tool does not map CPT to controlled-substance schedule.",
"maxLength": 10,
"type": "string"
},
"dea_number": {
"description": "9-char DEA registration (e.g. 'AB1234563').",
"maxLength": 10,
"type": "string"
}
},
"required": [
"dea_number"
],
"type": "object"
},
"name": "verify_dea_authorization",
"outputSchema": null
},
{
"description": "DEPRECATED ALIAS of verify_attestation — kept for backward compatibility with v0.1.7 clients. New code should call verify_attestation directly.\n\nWHEN TO USE: Reference lookups: individual code details, verifying a provider registry entry, checking a prior Medigami response's signature, or tracking an outcome.\n\nWHEN NOT: For composite workflows use the higher-level tool that calls these internally.",
"inputSchema": {
"properties": {
"envelope": {
"description": "The signed response envelope",
"type": "object"
},
"expected_fingerprint": {
"description": "SHA-256 hex of the PEM public key you trust",
"type": "string"
},
"public_key_pem": {
"description": "PEM public key content (preferred)",
"type": "string"
}
},
"required": [
"envelope"
],
"type": "object"
},
"name": "verify_mcp_response",
"outputSchema": null
},
{
"description": "Subscribe to an appeal outcome by tracking_id. Blocks up to `timeout_seconds` (default 300). Returns the outcome payload as soon as it's recorded, or {status: 'timeout'} if nothing resolved within the window — caller re-invokes to keep watching. Tracking ids are returned by estimate_appeal_success and other Tier 3 moat tools.\n\nWHEN TO USE: Caller wants to subscribe to the outcome of an in-flight appeal by tracking_id.\n\nWHEN NOT: One-shot queries — prefer the callbacks via /api/outcomes/record.",
"inputSchema": {
"properties": {
"timeout_seconds": {
"maximum": 600,
"minimum": 1,
"type": "integer"
},
"tracking_id": {
"maxLength": 32,
"type": "string"
}
},
"required": [
"tracking_id"
],
"type": "object"
},
"name": "watch_appeal_outcome",
"outputSchema": null
},
{
"description": "Subscribe to a claim denial event for a given scan_id. Blocks up to `timeout_seconds`. Returns {status: 'denied', ...} as soon as the payer marks the claim denied in claim_status_history, or {status: 'timeout'} if no denial observed within the window.\n\nWHEN TO USE: Caller wants to stream denial events for a set of claims.\n\nWHEN NOT: One-shot queries.",
"inputSchema": {
"properties": {
"scan_id": {
"maxLength": 128,
"type": "string"
},
"timeout_seconds": {
"maximum": 600,
"minimum": 1,
"type": "integer"
}
},
"required": [
"scan_id"
],
"type": "object"
},
"name": "watch_claim_denial",
"outputSchema": null
},
{
"description": "[Taxonomy III.41 — baseline response (public data only)] Report price variance for a CPT across ZIP3 regions with DP noise.\n\nWHEN TO USE: User wants to understand what a service typically costs, compare prices across regions/providers, or gauge whether a billed amount is reasonable.\n\nWHEN NOT: For a specific bill they have in hand, scan_bill_for_errors is more actionable. For insurance-path estimates, use deductible_impact_calculator or coinsurance_simulator.",
"inputSchema": {
"additionalProperties": true,
"properties": {},
"type": "object"
},
"name": "zip_based_price_variance",
"outputSchema": null
}
]
}Verify it yourself
curl -s https://api.teppi.xyz/v1/evidence/sha256:2505f92282514139fd2cd2fca684b013b6278201ce033812e39cd24242b400a3 | sha256sum