Skip to main content
Glama

Care: doctors, hospitals and nursing homes

check_care
Read-only

Returns clinicians from the federal NPI registry (CMS) for a name (last name, first name, state) or a specialty in a city or state: credential, specialty, state license number, practice address and phone, whether the record is active, and whether they opted out of Medicare. The registry is not a quality rating and does not show insurance networks. For hospitals and nursing homes, returns Medicare's ratings in a US city or ZIP code, highest rated first. Nursing homes include overall, health-inspection, staffing and quality stars, total fines, Medicare's abuse icon and stale inspections. Hospitals include the overall star rating, emergency services and safety measures better or worse than national. Each row includes a Medicare Care Compare link. Applies to questions about a clinician in the federal registry, or Medicare ratings for hospitals and nursing homes in a US place. Not medical advice; the person chooses their care.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "check_care"
  }
}

Input Schema

NameRequiredDescriptionDefault
zipNoHospitals and nursing homes: 5-digit ZIP code instead of city and state
cityNo
kindNoclinician (doctor, nurse practitioner, therapist and others), hospital or nursing_home; clinician when a name or specialty is sent
nameNoPart of a hospital's or nursing home's name, to check one place
limitNo
stateNoTwo-letter state
last_nameNoClinician's last name
specialtyNoClinician specialty, e.g. 'pediatrics', 'dermatology', 'family medicine', 'psychologist'
first_nameNoClinician's first name

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changed
    • addedInput schema / properties / first_name
      Added value: +{
      +  "description": "Clinician's first name",
      +  "maxLength": 60,
      +  "type": "string"
      +}
    • addedInput schema / properties / kind / description
      Added value: +"clinician (doctor, nurse practitioner, therapist and others), hospital or nursing_home; clinician when a name or specialty is sent"
    • changedInput schema / properties / kind / enum
      Previous value: -[
      -  "nursing_home",
      -  "hospital"
      -]New value: +[
      +  "clinician",
      +  "hospital",
      +  "nursing_home"
      +]
    • addedInput schema / properties / last_name
      Added value: +{
      +  "description": "Clinician's last name",
      +  "maxLength": 60,
      +  "type": "string"
      +}
    • changedInput schema / properties / limit / maximum
      Previous value: -15New value: +20
    • changedInput schema / properties / name / description
      Previous value: -"Part of a facility's name, to check one place"New value: +"Part of a hospital's or nursing home's name, to check one place"
    • addedInput schema / properties / specialty
      Added value: +{
      +  "description": "Clinician specialty, e.g. 'pediatrics', 'dermatology', 'family medicine', 'psychologist'",
      +  "maxLength": 80,
      +  "type": "string"
      +}
    • changedInput schema / properties / state / description
      Previous value: -"Two-letter state, with city"New value: +"Two-letter state"
    • changedInput schema / properties / zip / description
      Previous value: -"5-digit ZIP code instead of city and state"New value: +"Hospitals and nursing homes: 5-digit ZIP code instead of city and state"
    • removedInput schema / required
      Removed value: -[
      -  "kind"
      -]
  2. Added

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnly/openWorld/non-destructive, and the description adds substantive context on top: the upstream source (federal NPI registry, CMS), sort order ('highest rated first'), per-row Care Compare links, and data-quality caveats ('stale inspections', 'not a quality rating'). It leaves pagination/result-cap behavior for the `limit` parameter and the empty-call case unmentioned, so it is not a 5.

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?

Front-loaded with the primary entity and mode split, and every clause carries information (fields, sort order, caveats). There is mild redundancy between the opening mode description and the later 'Applies to questions about...' sentence, and the closing disclaimer is padding relative to the calling decision.

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

Completeness4/5

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

For a 9-parameter, zero-required, no-output-schema tool with two distinct modes, the description covers inputs, outputs, sorting and caveats well enough to call it correctly. The remaining gap is what an empty/partial call returns given all parameters are optional, which an agent could hit given zero required fields.

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?

Beyond the 78%-covered schema, the description explains the parameter combinations that actually select a mode: last name/first name/state or a specialty in a city or state for clinicians, city+state or ZIP for facilities, and that `name` is a facility-name filter. That mode mapping is real added meaning; `limit` and the all-optional empty-call behavior are never clarified.

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 specific verbs and resources: clinicians from the federal NPI registry (CMS) with named return fields, and Medicare ratings for hospitals and nursing homes in a US place. The two modes are explicitly separated with 'For hospitals and nursing homes, returns...', so an agent knows exactly what comes back for each branch.

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?

'Applies to questions about a clinician in the federal registry, or Medicare ratings for hospitals and nursing homes in a US place' gives positive triggers, and 'the registry is not a quality rating and does not show insurance networks' plus 'Not medical advice' give explicit when-not signals. It stops short of naming an alternative sibling (e.g. check_medicine) to route to, so it earns a 4 rather than a 5.

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