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

Annotations already declare readOnly/idempotent, so the bar is lower. The description adds real value beyond them: it discloses the confidence taxonomy (exact/strong/possible), that early-warning signals come from a distinct NHTSA/CPSC/PRESS/SEC pipeline, and that the receipt option stores a dated record for 400 days fetchable at verify_url and is explicitly not a safety certification.

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?

Front-loads the core question and the input flexibility, then covers returns and the signal caveat. The long enumerated sentence is dense but every clause carries information; the return-value detail is somewhat verbose given it appears before the caller has decided to use the tool.

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?

With no output schema, the description must explain returns, and it does: match confidence levels, per-match reasons, agency source links, plus early-warning signals and the receipt artifact. An agent has enough to call it and interpret the result without further documentation.

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 every parameter is already documented in the schema, putting the baseline at 3. The description restates the accepted identifier families (name+brand, UPC/EAN/GTIN, model, NDC, lot) but adds no format or disambiguation rules beyond the schema.

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?

Opens with a direct question ('Is this product recalled?') and names the resource and the recall sources checked (CPSC, FDA, NHTSA). It is clearly a product-recall lookup, distinct from the sibling check_vehicle.

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?

'Give whatever you have' tells the agent that any subset of identifiers works, which is useful input guidance, and 'A signal is not a recall' sets expectations. However, it never states when to use this tool versus get_recall or search_recalls, nor any exclusion conditions.

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