Skip to main content
Glama

Search NPI providers

search_npi_providers
Read-onlyIdempotent

Use this when the user wants an npi registry search, npi search or provider npi lookup by name and state. Reads live public registry records and returns Excel and CSV downloads. Up to 10 searches per call, with at most 10 matches each; give a last name or organization name and a US state. Do not use for insurance acceptance or patient records.

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": {
      "searches": "<searches>"
    },
    "name": "search_npi_providers"
  }
}

Input Schema

NameRequiredDescriptionDefault
searchesYesOne to ten name and state searches, e.g. [{"last_name":"Smith","first_name":"John","state":"MA"}].

Output Schema

NameRequiredDescriptionDefault
sourceYes
summaryYes
searchesYes
downloadsYes
providersYes
truncatedYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

The annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the description only needs to add context. It does add real value by disclosing that records are live public data, that results come as Excel and CSV downloads, and that caps are one call with up to 10 searches and at most 10 matches each. It doesn't explain what happens when a search returns no matches.

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?

Three sentences, all front-loaded and each carrying a distinct payload: usage trigger, behavioral/return facts, then limits/required inputs and exclusions. The synonym list for search intent is slightly redundant but serves intent matching without bloat.

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?

The output schema is present, so the description need not explain return shape, and the batch limits and required inputs are covered. The one shortfall is that the boundary with the verify_npi_numbers sibling is left implicit rather than stated.

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 description coverage is 100%, so the baseline is 3, but the description adds meaning beyond the schema: it states that a last name or organization name must be supplied alongside a US state, whereas the schema only marks 'state' as required. That resolves a real ambiguity about which name field to populate.

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?

The description uses specific verbs and resources: 'npi registry search', 'provider npi lookup by name and state', and adds scope ('reads live public registry records'). It does not name the sibling verify_npi_numbers, so an agent must infer the search-vs-verify distinction from the exclusion clause alone.

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

Usage Guidelines5/5

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

It explicitly says when to use it ('when the user wants an npi registry search ... by name and state'), how to use it ('give a last name or organization name and a US state'), and when not to ('Do not use for insurance acceptance or patient records'). The only gap is that it doesn't name verify_npi_numbers as the alternative.

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