recall-check

check_recall

Checks U.S. government recall records and returns the status with the agency's own links and a signed receipt. Give product (a name, matched against CPSC recall titles) or vehicle (model year, make, model, looked up at NHTSA). Returns status recalls_found with the newest recalls (id, title, date, summary, hazard, remedy, link) or none_found; confidence says how far to trust the search (CPSC matches title words; NHTSA is exact per model). Confidence unknown when the agency's answer could not be read. Call it before advising on a used product or vehicle, or when asked whether something has been recalled.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "check_recall"
  }
}

Input Schema

Name	Required	Description
`since`	No	Products only: ignore CPSC recalls announced before this date (YYYY-MM-DD). Narrows the list; it does not make a slow CPSC search faster.
`product`	No	Consumer product to check with the U.S. CPSC. Words matched against recall titles, which read like "Peloton Recalls Tread+ Treadmills", so use the brand or the product name, not both: "Tread+" or "Rock 'n Play". Fewer words match more. Give either product or vehicle, not both.
`vehicle`	No	Vehicle to check with the U.S. NHTSA by model year, make and model. Give either product or vehicle, not both.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 13, 2026

TDQS

A3.9/5.0

Behavior4/5

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

With no annotations supplied, the description carries the full burden, and it does substantial work: it discloses the two status outcomes, the returned fields, and the confidence semantics including the degraded state where confidence is unknown because "the agency's answer could not be read." It also warns that the `since` filter does not speed up slow CPSC searches. It says nothing about auth, rate limits, or error handling beyond the unreadable-answer case.

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 response shape and usage trigger are front-loaded, and every sentence conveys something operational. The middle sentence is long and semicolon-stacked, slightly reducing scannability, but there is no filler.

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?

There is no output schema, so the description must explain returns, and it does so thoroughly with status branches, field list, and confidence caveats. For a two-source lookup tool with nested vehicle params, the only meaningful omission is failure/error behavior beyond the unreadable-answer note.

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% and the field descriptions already explain matching behavior, model naming, and the date filter in detail. The description restates the agency-to-parameter mapping and adds the confidence rationale (CPSC matches title words, NHTSA is exact per model), but that is largely redundant with the schema rather than new guidance.

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 a specific verb and resource ("Checks U.S. government recall records") and scopes it to two named sources, CPSC for products and NHTSA for vehicles. It does not explicitly position itself against the only sibling, get_receipt, although the mention of "a signed receipt" hints at the handoff relationship.

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?

It gives concrete trigger conditions: "Call it before advising on a used product or vehicle, or when asked whether something has been recalled." It also states the mutual-exclusion constraint ("Give either product or vehicle, not both"). No explicit when-not-to-use or alternative routing is given, but the intended usage moment is unambiguous.

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

All recall-check tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?