Skip to main content
Glama

Check Provider Exclusion

check_provider_exclusion
Read-onlyIdempotent

Is this healthcare provider barred from Medicare, Medicaid and other federal health programs? Screens a person or business name, or an NPI, against the HHS OIG List of Excluded Individuals/Entities, the list you are required to check before paying, employing or contracting with a provider. Answers "is Dr X excluded", "check this provider against the OIG exclusion list", "has this practice been barred from Medicare", and pre-payment or credentialing screening. Returns matching exclusions with the date of birth, state, city, specialty and NPI that tell same-named people apart, plus when the exclusion started and the statutory reason for it, and a match_confidence saying what was actually matched. Never returns a bare yes/no: several excluded people can share a name, so identifying the right one is the caller's job and this gives them what they need to do it. Pass npi to turn a name lead into an identification. Sourced from HHS OIG.

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"
    },
    "name": "check_provider_exclusion"
  }
}

Input Schema

NameRequiredDescriptionDefault
npiNoThe provider's 10-digit NPI, if you have it. An NPI match is an identification rather than a name lead, always pass it when known.
nameNoProvider or business name to screen, e.g. "John Smith" or "Acme Home Health". Any order; surname-first works too.
limitNoMaximum candidates to return (default 10, max 50).
stateNoTwo-letter state code to narrow candidates, e.g. "CA". Useful when a common name returns several people.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / npi / description
      Previous value: -"The provider's 10-digit NPI, if you have it. An NPI match is an identification rather than a name lead — always pass it when known."New value: +"The provider's 10-digit NPI, if you have it. An NPI match is an identification rather than a name lead, always pass it when known."
  2. First observed

TDQS

A4/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description does add genuinely useful behavior beyond that: it returns DOB, state, city, specialty, NPI, exclusion start date, statutory reason and a match_confidence, and explicitly refuses to return a bare yes/no. That is strong disclosure of result semantics and of the caller's disambiguation burden.

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-loads the core question, then usage examples, then return shape — a sensible ordering. It is somewhat long and repeats the NPI-as-identification point at the end after already making it earlier, costing a little efficiency.

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 no output schema, the description carries the return-value burden itself and does so: it lists the identifying fields, the exclusion dates and reason, and the match_confidence concept. It also sets expectations that results are candidate matches rather than confirmations, which is exactly the context needed to call and interpret it.

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 coverage is 100%, so the schema already documents npi, name, limit and state, including the note that an NPI match is an identification rather than a name lead. The description's "pass npi to turn a name lead into an identification" largely restates that, and it says nothing extra about limit or state beyond 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?

Opens with a specific question the tool answers and names the exact resource: screening a person/business name or NPI against the HHS OIG List of Excluded Individuals/Entities. It is immediately distinguishable from a general entity or coverage lookup, and the scope (federal health program exclusions) is unambiguous.

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?

Gives concrete triggering questions ("is Dr X excluded", "has this practice been barred from Medicare") and names the workflows it serves — pre-payment and credentialing screening. It does not state when NOT to use it or point to any alternative (a sibling like provider_exclusion_coverage is never referenced), so guidance is clear but not exclusionary.

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.