Skip to main content
Glama

NS Pros MCP Gateway

npi-registry__npi_registry_search

Search providers by any combination of fields. NPI Registry requires at least one filter, supply at least name/organization/taxonomy/postal_code/state.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "name": "John Smith",
      "state": "CA",
      "taxonomy": "Internal Medicine"
    },
    "name": "npi-registry__npi_registry_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
cityNo
nameNoFull provider name (use along with type)
skipNo0-based offset (max 1000)
limitNo1-200 (default 10)
stateNoTwo-letter state code
numberNo10-digit NPI
npi_typeNoNPI-1 (individual) | NPI-2 (organization)
taxonomyNoTaxonomy code or description (e.g. "Internal Medicine")
last_nameNo
first_nameNo
postal_codeNo5-digit ZIP (or first 3 with wildcard "*")
country_codeNoUS (default) | other ISO country
address_purposeNoLOCATION (default) | MAILING | PRIMARY | SECONDARY
organization_nameNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.4/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full disclosure burden. It contributes one genuinely behavioral fact — that the registry rejects calls with no filter — but says nothing about result ordering, pagination behavior, or what happens on failure, all of which matter for a 14-parameter query tool.

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

Conciseness5/5

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

Two sentences, zero filler, with the core purpose front-loaded and the hard constraint immediately after. Nothing is repeated from the schema and nothing extraneous is included.

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

Completeness2/5

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

For a 14-parameter search with no annotations and no output schema, the definition is thin: it never indicates what a result contains, whether pagination metadata is returned, or how many records a query can yield. The agent knows how to make the call legal but not what it will get back.

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 71%, so the schema already documents most parameters (skip offset max 1000, limit 1-200, ZIP wildcard, npi_type, address_purpose). The description adds a useful semantic layer by singling out the five fields that satisfy the required-filter rule, but it leaves the undescribed ones (city, first_name, last_name, country_code, organization_name) unclarified and doesn't explain the name+npi_type pairing noted in the schema.

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

Purpose4/5

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

States a specific verb and resource: 'Search providers by any combination of fields.' This is clearly a multi-filter provider search rather than a single-record lookup, so an agent can distinguish it from a by-NPI fetch. It stops short of naming any sibling (e.g. search_within) or contrasting scope with them.

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

Usage Guidelines3/5

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

The second sentence gives a real operational precondition: at least one of name/organization/taxonomy/postal_code/state must be supplied, which prevents a guaranteed-empty call. However, there is no guidance on when to prefer this over a single-provider lookup or narrower search, and no mention of what to do when results are too broad.

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.