Skip to main content
Glama

Product Recalls API - FDA, CPSC, Vehicle, Canada, UK

product_recalls
Read-onlyIdempotent

Search 130,000+ official recalls from 5 government sources in one call: US FDA (food, drugs, medical devices), CPSC (consumer products), NHTSA (vehicles), Health Canada (incl. CFIA food, Transport Canada) and UK Food Standards Agency (allergy alerts). One normalized row: product, brand, reason, hazard, class, date, remedy, official link. Filter by words, brand, vehicle make/model/year, country, category, class, date. Index refreshed every 6 h, answers < 1 s. Free: 25 calls/day per IP. Paid: $0.002 per call via x402 at https://radarbg.com/x402/product-recalls.

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": {
      "limit": 10,
      "query": "salmonella",
      "sinceDays": 90
    },
    "name": "product_recalls"
  }
}

Input Schema

NameRequiredDescriptionDefault
makeNoVehicle make, e.g. Honda
modeNosearch or sources (freshness of each source)search
yearNoVehicle model year (needs make), e.g. 2020
brandNoBrand or recalling company, e.g. Tesco, Olymel
limitNoMax recalls, newest first (default 25, max 100)
modelNoVehicle model (needs make), e.g. Accord
queryNoWords that must appear: product, ingredient, hazard, lot or model, e.g. peanut, listeria
sinceNoOnly recalls on or after YYYY-MM-DD
untilNoOnly recalls on or before YYYY-MM-DD
sourceNofda, cpsc, nhtsa, health_canada or uk_fsa (comma list)
countryNoUS, CA or UK (comma list; empty = all)
categoryNofood, drug, medical_device, consumer_product, vehicle or cosmetic (comma list)
sinceDaysNoOnly recalls from the last N days
classificationNoI, II, III (most serious = I) or a UK alert type like allergy alert

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / limit / minimum
      Added value: +0
    • addedInput schema / properties / sinceDays / minimum
      Added value: +0
  2. First observed

TDQS

A4.1/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint, so safety and determinism need no restating. The description still adds genuinely useful operational context the annotations do not: a 6-hour index refresh, sub-second responses, a 25 calls/day free tier per IP, and $0.002/call paid access via x402. It does not cover pagination behavior beyond the limit param or failure modes, so it is strong added context rather than complete.

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?

Four tight sentences with the scope front-loaded, then output shape, then filter axes, then freshness/pricing. Every clause carries decision-relevant information and nothing is repeated.

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?

For a 14-parameter, no-required-arg search tool with no output schema, the description supplies the missing return-shape information ("One normalized row: product, brand, reason, hazard, class, date, remedy, official link") along with freshness and quota limits. That covers what an agent needs to call it and interpret results without opening anything else.

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 one of the 14 parameters is already documented, including the make/model/year dependency and the classification enum with severity ordering. The description's filter summary (words, brand, vehicle make/model/year, country, category, class, date) mostly restates that surface and adds no syntax or format detail of its own. Baseline 3 is appropriate when the schema carries the semantics.

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?

States a specific verb and resource ("Search 130,000+ official recalls") and enumerates the five covered sources (FDA, CPSC, NHTSA, Health Canada, UK FSA) with the categories each covers. An agent can immediately tell this is a consolidated recall search rather than a single-regulator lookup.

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 "from 5 government sources in one call" framing makes clear when this tool is the right consolidation choice, and the listed filter axes show the query shapes supported. It stops short of explicit when-not conditions or naming an alternative for single-source or non-recall lookups, so it is clear context without exclusions.

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