[PAID $0.01 USDC/call, x402, eip155:8453] Search official recall notices (CPSC, openFDA food/drug/device, RappelConso FR) by product, brand or model; filter by market and period.
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | Look-back period in days (default 365) | |
| limit | No | Max results per source (default 10) | |
| query | Yes | Product, brand or model, e.g. stroller, peanut butter, Facom | |
| market | No | all (default), us or fr |
Changes observed during successful MCP inspections.
Input schema / properties / days / maximumAdded value: +3650Input schema / properties / days / minimumAdded value: +1Input schema / properties / days / typePrevious value: -"number"New value: +"integer"Input schema / properties / limit / maximumAdded value: +25Input schema / properties / limit / minimumAdded value: +1Input schema / properties / limit / typePrevious value: -"number"New value: +"integer"Input schema / properties / market / enumAdded value: +[
+ "all",
+ "us",
+ "fr"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, but the description carries the key behavioral trait: this is a paid call ($0.01 USDC, x402, eip155:8453), so the agent knows payment is required before invoking. It does not disclose result aggregation behavior, failure modes, or whether results are deduplicated across the four sources.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence with the payment precondition front-loaded in brackets, followed by the resource, sources, and filtering capability. No filler; every clause adds information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
All parameters are documented in the schema, and the description names all four data sources, so an agent can call it correctly. With no output schema, a brief note on result shape (per-source lists capped by limit) would have closed the remaining gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so all four parameters (query, market, days, limit) are already documented with examples, defaults and ranges. The description's 'filter by market and period' only restates what the schema says, adding no format or semantic detail beyond it — baseline 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (Search) plus resource (official recall notices) and enumerates the actual sources (CPSC, openFDA, RappelConso FR) and searchable fields (product, brand, model). This implicitly distinguishes it from the sibling gtin_recall (barcode-based lookup), though no sibling is named explicitly.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description conveys the context of use (finding recall notices by product/brand/model, scoped by market and period) but never states when to prefer this over gtin_recall or pre_purchase_check, nor any when-not conditions. Usage is implied rather than prescribed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.