Skip to main content
Glama
cliwant

mcp-sam-gov

by cliwant

openfda_enforcement

Read-only

Search FDA recall and enforcement records for drugs, devices, or foods. Filter by firm, product, reason, classification, status, and state.

Instructions

Search openFDA recall/enforcement records — drug/device/food product recalls with the recalling firm, product, reason, FDA classification (Class I/II/III), status, and geography (openFDA /{category}/enforcement.json; api.fda.gov). KEYLESS (an OPTIONAL free OPENFDA_API_KEY only RAISES the rate limit — keyless works at ~1000 requests/day; it NEVER throws for a missing key; get one at https://open.fda.gov/apis/authentication/; call api_key_status to see every source's key requirement). Input: category (drug|device|food, default drug), and STRUCTURED filters — firm (→recalling_firm), product (→product_description), reason (→reason_for_recall), classification (Class I|II|III), status (e.g. Ongoing/Terminated/Completed), state (2-letter, e.g. 'CA') — the tool safely assembles + escapes these into the openFDA search= Lucene string (NO raw passthrough — injection-safe), plus limit (1..100, default 25) and skip (offset ≥0). Returns { recalls:[{ recallingFirm, productDescription, reasonForRecall, classification, status, state, city, recallInitiationDate, recallNumber, voluntaryMandated, distributionPattern }] } + honest _meta. HONESTY: totalAvailable is openFDA's EXACT meta.results.total (skip/limit pagination via hasMore/nextOffset — never results.length); every scalar (dates included, recall_initiation_date is a YYYYMMDD string) is null-never-empty-string. ★A no-match query returns openFDA HTTP 404 NOT_FOUND ⇒ an HONEST EMPTY (returned:0, totalAvailable:0), NOT an error; a 400 syntax error ⇒ invalid_input surfacing openFDA's message; a 5xx ⇒ THROWS; a 200 non-JSON ⇒ schema_drift. The optional key rides ONLY the &api_key= query param — never logged or echoed.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
firmNoRecalling firm name filter (→ recalling_firm), e.g. 'pfizer'. Matched as an escaped Lucene phrase.
skipNoRow offset for pagination (default 0). Page with _meta.pagination.nextOffset.
limitNoMax recall records to return (default 25, max 100). Offset-paginated via skip.
stateNo2-letter US state/territory postal code filter (→ state), e.g. 'CA'. Validated ^[A-Za-z]{2}$.
reasonNoReason-for-recall filter (→ reason_for_recall), e.g. 'contamination'. Matched as an escaped Lucene phrase.
statusNoRecall status filter (→ status), e.g. 'Ongoing', 'Terminated', 'Completed'.
productNoProduct description filter (→ product_description), e.g. 'insulin'. Matched as an escaped Lucene phrase.
categoryNoThe recall category (default 'drug'): 'drug', 'device', or 'food'. Selects the openFDA /{category}/enforcement endpoint.
classificationNoFDA recall classification filter: 'Class I' (most serious), 'Class II', or 'Class III'.
Behavior5/5

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

The description extensively covers behavioral traits beyond annotations: keyless operation, error handling (404→empty, 400→invalid_input, 5xx→throws, 200 non-JSON→schema_drift), honest pagination with totalAvailable exact, null-never-empty strings, and safe Lucene query construction. No contradiction with annotations (readOnlyHint=true, openWorldHint=true).

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?

The description is relatively long but well-structured with clear sections and bullet points. It front-loads the purpose and keyless info, then details parameters and error handling. Every sentence adds necessary information; minor room for trimming but overall efficient.

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?

Despite no output schema, the description fully documents the return structure (recalls array with fields, _meta with totalAvailable and pagination tokens) and all edge cases (empty response, errors). It is self-contained and complete for agent usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the description adds significant value by explaining the mapping of filters to openFDA fields (e.g., firm→recalling_firm), the default category, safe injection-free Lucene string assembly, and validations (e.g., state format). This goes well beyond the schema alone.

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?

The description clearly states it searches openFDA recall/enforcement records, listing specific categories (drug/device/food) and data fields. It distinguishes itself from sibling tools like openfda_device_clearances and openfda_drug_approvals by focusing on enforcement/recalls.

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?

The description explains how to use filters, pagination, keyless vs. keyed access, and error handling. It doesn't explicitly state when not to use this tool, but it's clear this is for enforcement data; alternatives are implied by sibling tool names. The honesty about rate limits and error cases is helpful.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/cliwant/mcp-sam-gov'

If you have feedback or need assistance with the MCP directory API, please join our Discord server