Skip to main content
Glama
cliwant

mcp-sam-gov

cpsc_recalls

Read-only

Find U.S. CPSC consumer-product recalls by date, product, manufacturer, or recall number. Get recall title, hazard, remedy, affected products, injuries, and more from SaferProducts.gov.

Instructions

Look up U.S. CPSC consumer-product RECALLS — recall title, hazard description, remedy, affected products, manufacturers, retailers, injuries, and country of manufacture (CPSC SaferProducts /RestWebServices/Recall; www.saferproducts.gov). KEYLESS. Siblings: nhtsa_recalls (vehicles), openfda_enforcement. Inputs (ALL optional): dateStart/dateEnd (YYYY-MM-DD recall date range), productName (substring), manufacturer (substring), recallNumber. Returns { recalls:[{ recallNumber, recallDate, title, description, url, products:[names], numberOfUnits, manufacturers:[names], retailers:[names], hazards:[descriptions], remedies:[descriptions], injuries:[names], manufacturerCountries:[names] }] } + honest _meta. HONESTY: the CPSC response is a bare array with NO count field and NO pagination — it returns the COMPLETE matching set, so totalAvailable = number of returned recalls and complete:true (never a fabricated total). ★With NO filter given, results are bounded to a DEFAULT ~90-day recent window (RecallDateStart, disclosed in _meta.notes) rather than a silent whole-dataset fetch. Empty result → HONEST EMPTY (returned:0), NOT an error; 4xx → invalid_input; 5xx/timeout → THROWS; 200 non-JSON or non-array → schema_drift. Nested arrays are flattened to name/description strings; NumberOfUnits kept as a string; every scalar is null-never-empty-string. Fixed host (SSRF-guarded); dates are ^\d{4}-\d{2}-\d{2}$ and recallNumber is letters/digits/hyphen only.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dateEndNoRecall date range END (optional), YYYY-MM-DD, e.g. '2025-01-31' (→ RecallDateEnd). Validated ^\d{4}-\d{2}-\d{2}$.
dateStartNoRecall date range START (optional), YYYY-MM-DD, e.g. '2025-01-01' (→ RecallDateStart). Validated ^\d{4}-\d{2}-\d{2}$.
productNameNoProduct name substring filter (optional), e.g. 'helmet' (→ ProductName).
manufacturerNoManufacturer name substring filter (optional) (→ Manufacturer).
recallNumberNoA specific CPSC recall number (optional), e.g. '25088' (→ RecallNumber). Letters/digits/hyphen only (^[A-Za-z0-9-]+$).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.12.0

TDQS

A4.4/5.0
Behavior5/5

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

Beyond the readOnlyHint/openWorldHint annotations, the description discloses an exceptional behavioral contract: the CPSC response is a bare array with no count field and no pagination, so totalAvailable always equals the number of returned recalls and complete:true is never fabricated; a default ~90-day window applies when no filter is given; empty results are honest empties not errors; 4xx maps to invalid_input, 5xx/timeout throws, and 200 non-JSON/non-array maps to schema_drift; normalization rules (flattened arrays, NumberOfUnits as string, null-never-empty-string) are specified. This fully arms an agent against misinterpreting the response.

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 dense (~200 words) but every sentence carries information: purpose, auth stance, sibling routing, inputs, return shape, honesty contract, error mappings, and normalization. The ALL-CAPS markers (KEYLESS, HONESTY) break the wall of text into scannable segments. It loses one point because the HONESTY sentence is a long run-on packing several distinct behaviors into one clause chain, but nothing is wasted.

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 fully specifies the return shape including every recall field and the honest _meta object. It also covers the quirky API contract (no pagination, no count, default window, error taxonomy, input validation rules) that an agent could not infer otherwise. The read-only safety profile is handled by annotations. Nothing an agent needs to call this tool correctly or interpret its result is left unsaid.

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% — every parameter already carries a description, example, and validation regex, so the schema does the heavy lifting. The description adds only marginal value: the 'ALL optional' note and a prose restatement of the date/substring filter semantics already present in the schema. Baseline 3 is appropriate under high coverage.

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 opens with a specific verb-resource pair, 'Look up U.S. CPSC consumer-product RECALLS', and enumerates the exact content covered (hazard description, remedy, affected products, manufacturers, retailers, injuries, country of manufacture). It also names the nearest confusable siblings (nhtsa_recalls for vehicles, openfda_enforcement) so an agent can distinguish this tool without opening their schemas.

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 sibling list with parenthetical scopes ('nhtsa_recalls (vehicles)', 'openfda_enforcement') gives a clear routing signal: consumer-product recalls go here, vehicle recalls and FDA enforcement go to the named alternatives. It also states that all inputs are optional and discloses the default 90-day window when no filter is given. The exclusions are implied through sibling hints rather than explicit 'use X instead when...' prose, which keeps this just shy of a 5.

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

Deploy Server

Other Tools