Skip to main content
Glama

Fda Inspections

fda_inspections
Read-onlyIdempotent

FDA inspection results with their final classification, NAI (no action indicated), VAI (voluntary action indicated) or OAI (official action indicated, the serious one). Covers FDA-regulated establishments worldwide (drug, device, food, biologics), not just US sites. Search by firm name (substring), state, country, product type or date range. Source: FDA Data Dashboard (OII). This is inspection OUTCOME data, openFDA does not carry it.

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": {
      "firm": "Intas",
      "limit": 25
    },
    "name": "fda_inspections"
  }
}

Input Schema

NameRequiredDescriptionDefault
firmNoFirm legal-name substring, e.g. "Intas" or "Sun Pharma".
limitNoRows to return (default 50, max 5000).
sinceNoEarliest inspection end date, YYYY-MM-DD.
stateNoUS state, as a postal code ("NJ") or full name ("New Jersey"), both work. Foreign sites carry no state; filter those by country.
untilNoLatest inspection end date, YYYY-MM-DD.
_apiKeyNoFDA Data Dashboard credential as "email:key", the e-mail the credential was issued to, then the FDA-generated key, joined by a colon.
countryNoCountry name as FDA spells it, e.g. "India", "China".
fiscal_yearNoFDA fiscal year, e.g. "2026".
product_typeNoe.g. "Drugs", "Devices", "Foods", "Biologics".
classificationNoFinal classification: NAI, VAI or OAI. OAI is the one that signals enforcement risk.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / _apiKey / description
      Previous value: -"FDA Data Dashboard credential as \"email:key\" — the e-mail the credential was issued to, then the FDA-generated key, joined by a colon."New value: +"FDA Data Dashboard credential as \"email:key\", the e-mail the credential was issued to, then the FDA-generated key, joined by a colon."
    • changedInput schema / properties / state / description
      Previous value: -"US state, as a postal code (\"NJ\") or full name (\"New Jersey\") — both work. Foreign sites carry no state; filter those by country."New value: +"US state, as a postal code (\"NJ\") or full name (\"New Jersey\"), both work. Foreign sites carry no state; filter those by country."
  2. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, non-destructive and open-world, so safety is covered; the description adds what the data represents (inspection outcomes, not citations or actions), its global scope, and its provenance. It omits the operational detail most likely to trip an agent: that an FDA Data Dashboard credential (_apiKey) is needed to call this at all.

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 core purpose, then scope, then filters, then source — a sensible ordering. Parenthetical glosses on NAI/VAI/OAI are slightly wordy but each earns its place by preventing misreading of the codes.

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?

With 10 parameters, no output schema and no required fields, the description gives enough to search correctly and interpret the classification output. The main gap is that credential requirements and result-set/pagination behavior are left entirely to the schema, and no sibling routing is offered.

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 every parameter, including _apiKey and the state/country distinction, is already documented in structured form; the description only restates the filter list. Its one genuine addition is the semantic gloss on classification values (OAI = the serious one, signals enforcement risk), which helps interpretation rather than invocation.

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?

"FDA inspection results with their final classification" names a specific resource and the key attribute, then the description expands what NAI/VAI/OAI mean so an agent can interpret results. It also states the covered population (FDA-regulated establishments worldwide) and the data source, so the tool 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 Guidelines3/5

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

It gives implied usage (search by firm/state/country/product type/date range) and one contrast with an external data source ("openFDA does not carry it"), which tells the agent when this tool is the right one. It does not route against the sibling tools that exist here (fda_483_citations, fda_compliance_actions, fda_import_refusals), so the when-vs-alternative guidance stays implicit.

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.