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

Annotations already cover read-only/open-world/idempotent, so the description's added value is the provenance caveats: complaints are unverified by NHTSA and not a safety determination, campaigns are filed at model level, and per-vehicle repair status is not available here. That is meaningful behavioral context beyond the annotations, though return shape and any rate/timeout behavior are still unstated.

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 what the tool returns (campaigns, then complaint counts) before the caveats, and every sentence carries information. The final sentence about dealer records is somewhat tangential and the sentences are long, keeping it from a 5.

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 correctly takes on the burden of describing return content (campaigns plus complaint counts), data sources, and the limits of those results. It is close to complete for a two-mode read tool, though it does not describe result ordering or volume.

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?

With 100% schema coverage the baseline is 3, but the description adds genuine meaning: the vin is '17-character' and decoded via NHTSA vPIC, and the either/or relationship between vin and the make/model/year triple is stated centrally. This goes a step beyond the schema, which repeats the same either/or line per property.

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: NHTSA recall campaigns for a vehicle, retrievable by VIN or make/model/year, plus complaint counts. The scope is unmistakable and implicitly separates it from check_product by focusing on vehicles. It never names a sibling tool, so it earns a 4 rather than a 5.

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 either vin, or make, model and year' supplies a clear input-selection rule, and the closing sentence explains when this tool's data is insufficient (vehicle-level inclusion and repair completion live in maker records, checkable by any dealer with the VIN). It stops short of naming check_product or search_recalls as alternatives for other cases.

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