Skip to main content
Glama

What does a procedure cost at hospitals near this ZIP? Cash price, gross charge and every insurer’s negotiated rate for a CPT, HCPCS or MS-DRG code at Colorado hospitals, normalized by Distill from the hospitals’ federally required price files

hospital_prices
Read-only

What does a procedure cost at hospitals near this ZIP? Cash price, gross charge and every insurer’s negotiated rate for a CPT, HCPCS or MS-DRG code at Colorado hospitals, normalized by Distill from the hospitals’ federally required price files. From the machine-readable standard-charge files hospitals must publish (45 CFR 180), parsed and normalized: for each hospital within the radius that posts the code, nearest first, the gross charge, the discounted cash price, the de-identified minimum and maximum, and every payer and plan’s negotiated dollar amount or percentage (with the v3.0 median, 10th and 90th percentile allowed amounts), payers canonicalized to a stable payer_id. Filters: payer, plan type, plan name text, setting, billing class. A summary gives nearest-rank statistics over the hospitals returned. Served states: Colorado. An area with no hospital posting the code answers 404 and is not charged. Refreshed monthly (live freshness: /status). Price: $0.02 per call. Free tier: 3 free calls a day per IP, at most 3 rows per answer, taken by an unpaid call unless its _meta["distill/free-tier"] is "skip". Answers in a summary view of about 3,000 tokens; view: "full" for every row. Confidence: Mean over the returned rows (each rate; an item with no rate counts once) of normalize × quality × freshness. Normalize: the stored per-rate normalize confidence (payer canonicalization: rule 1, model 0.9, fallback 0.6; rate basis for rates with no dollar amount: rule 1, model 0.9, fallback 0.75; 1 for an item with no rate). Quality of the MRF: 1 valid against the v3.0 schema, 0.85 parsed with conformance errors, 0.7 parsed only after header repair. Freshness: 1 while the MRF’s last_updated_on is at most 365 days old, then halving every 180 days (0.5 with no date), times 1 within 14 days of our fetch, then halving every 30 days. Posted standard charges from hospital machine-readable files (45 CFR 180): posted rates, not a quote; not medical or financial advice. What you pay depends on your plan, your care and the hospital. See /terms.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "code": "<code>"
    },
    "name": "hospital_prices"
  }
}

Input Schema

NameRequiredDescriptionDefault
latNoLatitude of the point (with lon).
lonNoLongitude of the point (with lat).
zipNoA 5-digit ZIP code (its Census ZCTA point). Give a zip, or lat and lon.
codeYesThe billing code: CPT (5 characters, e.g. 99213), HCPCS Level II (a letter and 4 digits, e.g. J1885) or MS-DRG (3 digits, e.g. 470).
planNoOptional: text the plan name (or payer name) contains as the hospital writes it, case-insensitive, e.g. "PPO" or "Medicare Advantage".
viewNosummary (the default): the answer a model needs, budgeted; full: every row (a free answer stays capped).
limitNoHow many hospitals to return, nearest first (default 10, at most 50).
payerNoOptional: a canonical payer_id (e.g. aetna, cigna, unitedhealthcare, anthem, medicare, medicaid). hospital.payers lists the payers with prices for a code.
settingNoOptional: inpatient or outpatient (items posted for both always match).
code_typeNoOptional: the code type. Inferred from the code’s shape when omitted.
plan_typeNoOptional: the canonical plan type.
radius_milesNoSearch radius in miles (default 25, at most 100).
billing_classNoOptional: facility or professional (items posted for both always match).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / view
      Added value: +{
      +  "description": "summary (the default): the answer a model needs, budgeted; full: every row (a free answer stays capped).",
      +  "enum": [
      +    "summary",
      +    "full"
      +  ],
      +  "type": "string"
      +}
  2. First observed

TDQS

A4.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes far beyond the annotations: discloses cost ($0.02/call), the 3-free-calls-per-day cap with its 3-row truncation and the _meta skip escape, monthly refresh cadence, the ~3,000-token summary budget versus view:"full", and the exact confidence computation (normalize × quality × freshness with all sub-rules). That is unusually rich disclosure for a read-only tool. Minor deduction because the placement and density of the confidence formula make the operational facts (cost, free-tier cap, 404) harder to extract than they should be.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loading is good — the purpose question leads and the payer/statistics description follows — but the prose is a single dense block in which the confidence formula consumes several sentences that matter more for interpreting output than for selecting or invoking the tool. Pricing, free-tier, and 404 behavior are buried mid-paragraph rather than given their own scannable position.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 13 parameters and no output schema, the description carries the full burden and does so: it explains row ordering (nearest first), the summary statistics block, the two view modes and their row budgets, the de-identification of min/max, payer canonicalization to payer_id, and what a valid answer versus a 404 looks like. An agent has everything needed to call it and to interpret the response.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description adds real meaning on top by grouping the filters (payer, plan type, plan name text, setting, billing class), stating that results are nearest-first with default 10 and max 50, and clarifying that view:"summary" is the budgeted default while "full" returns every row but stays capped on free answers. The lat/lon versus zip exclusivity is left to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific question it answers (what a procedure costs at hospitals near a ZIP), the exact resource (gross charge, cash price, per-payer negotiated rates) and the code systems accepted (CPT, HCPCS, MS-DRG), plus the geographic scope (Colorado only). This is clearly distinguishable from siblings like medicare_pfs_rate or drug_nadac, which cover fee schedules and drug pricing rather than hospital-posted standard charges.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Offers clear situational context: requires a code plus either zip or lat/lon, only serves Colorado, answers 404 without charge when no hospital posts the code, and is free-tier capped at 3 calls/day. It never explicitly names a sibling tool as the alternative when a caller wants a Medicare fee schedule or a drug price, so the routing guidance is implicit rather than spelled out.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources