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

Goes well past the readOnly/idempotent annotations: it discloses the response shape (normalized recall number, date, hazard/reason, remedy, link, newest first, plus anyRecall flag), the 400 error body format, and the paid-call mechanics ($0.002 USDC on Base, retry with params._meta["x402/payment"], plus a plain-HTTP GET fallback). Payment and retry behavior is exactly the kind of operational detail annotations cannot convey.

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 purpose and agency coverage before the return, error, and payment details, and every clause carries information an agent needs. It is dense — the HTTP endpoint and payment-retry sentence are heavy — but nothing is redundant.

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?

For a 9-parameter, zero-required tool with no output schema, the description covers what the tool does, which inputs map to which source, the return record fields and ordering, the error contract, and the x402 payment flow. An agent has everything needed to call it correctly and handle the paid retry.

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 78%, so the schema already documents most fields; the description adds the routing meaning that the schema lacks — that VIN drives decoded make/model/year lookups, UPC/name drive CPSC, and q is the general keyword path across FDA/NHTSA. It does not clarify how multiple params combine (AND vs. precedence), leaving one gap.

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 and resource ('product and vehicle recall lookup') and itemizes the three sources with their query modes (NHTSA by VIN/make-model-year, CPSC by UPC/name, FDA enforcement reports). No sibling tool overlaps, so the agent can distinguish it from climate_day, sanctions_address_check, and sec_filings at a glance.

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?

Gives an explicit use context ('safety checks before buying, selling or using a product or vehicle') and implies which input mode to pick per agency. It does not spell out when *not* to use it or name an alternative, but the sibling set contains no competing recall tool, so the guidance is sufficient in practice.

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