mcp

medigami_roast

Read-onlyIdempotent

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.

WHEN TO USE: Reference lookups: individual code details, verifying a provider registry entry, checking a prior Medigami response's signature, or tracking an outcome.

WHEN NOT: For composite workflows use the higher-level tool that calls these internally.

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": {
      "hospital": "<hospital>",
      "cpt": "<cpt>",
      "billed_amount": "<billed_amount>"
    },
    "name": "medigami_roast"
  }
}

Input Schema

Name	Required	Description
`cpt`	Yes	CPT/HCPCS procedure code.
`hospital`	Yes	Hospital / facility name.
`billed_amount`	Yes	Amount billed, USD.

Output Schema

Name	Required	Description	Default
`cta`	No
`rows`	No
`as_of`	No
`basis`	No
`command`	Yes
`refused`	No
`permalink`	Yes
`source_url`	Yes
`unresolved`	No
`result_kind`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 7, 2026

TDQS

A3.6/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds value beyond annotations by disclosing data provenance (public regulator data), privacy treatment (k-anonymity floored, implying returned values may be coarsened), and a legal disclaimer (not legal advice). No contradiction with the annotations.

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

Conciseness4/5

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

The core function is front-loaded in one tight sentence, with caveats compressed into a short clause (k-anonymity floored, not legal advice) and usage guidance cleanly separated into WHEN TO USE / WHEN NOT blocks. Slight deduction because the four-item WHEN TO USE list is padded with off-topic lookup/verify scenarios for a comparison tool.

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

Completeness3/5

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

Moderate complexity (3 required params, no enums, no nesting) with an output schema and rich annotations, so the description need not re-explain return values or side effects. It covers purpose, data provenance, privacy flooring, and a high-level when-not, but the mismatched WHEN TO USE scenarios and the unnamed higher-level composite tool are real gaps an agent must navigate.

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

Parameters3/5

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

Schema description coverage is 100%, so each parameter (cpt, hospital, billed_amount) is already documented in the schema. The description loosely echoes the schema in prose (billed charge, hospital's MRF rate, CPT code) but adds no new format, constraint, or edge-case semantics, so the baseline of 3 applies.

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 verb+resource: compares a billed charge against the hospital's own MRF-published negotiated rate for a CPT code, and names the return value (markup multiple). Naming the data source (MRF) and the exact comparison target distinguishes it from siblings like medigami_rate, billing_charge_vs_allowed_delta, and fair_price_estimator without needing their schemas.

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

Usage Guidelines2/5

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

Explicit WHEN TO USE / WHEN NOT sections exist, but the listed scenarios (individual code details, verifying a provider registry entry, checking a response signature, tracking an outcome) do not match this tool's function of computing a markup multiple — they read like boilerplate from a lookup/verify tool. No specific sibling alternative is named, and the WHEN NOT refers only to an unnamed 'higher-level tool', leaving the agent to guess which one.

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

All mcp tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?