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

Annotations already cover the safety profile (readOnly, idempotent, openWorld), yet the description adds substantial domain behavior: complaint counts are unverified by NHTSA and not a safety determination, campaigns are filed at model level rather than per-vehicle, and whether a specific vehicle is covered or repaired lives in the maker's records and must be checked by a dealer with the VIN. This is real disclosure beyond structured fields.

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?

Three sentences, front-loaded with the core capability before the caveats, and every sentence carries information. The closing sentence about dealer verification is somewhat peripheral but still useful for interpreting the result, so it earns its place.

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?

There is no output schema, so the description should describe the return shape more fully; it only says campaigns and complaint counts are returned. The bigger gap is invocation correctness: with 0 required parameters, the description never clarifies the required VIN-or-YMM combination, leaving an agent able to call it with an incomplete argument set.

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 description coverage is only 25% and there are 4 parameters with 0 required, so the description needs to compensate. It explains that the VIN is 17 characters and decoded with NHTSA vPIC and that make/model/year drive the campaign and complaint lookups, but it never states that either a VIN or the make/model/year combination must be supplied, nor whether both may be passed together or how they interact.

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?

The description states a specific verb and resource: NHTSA recall campaigns for a vehicle, plus consumer complaint counts, retrieved by VIN or by make/model/year. It is not a tautology and is far more specific than the title. It does not, however, distinguish itself from siblings like get_recall or search_recalls, so an agent cannot confidently route between them from this text alone.

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?

Usage is implied rather than stated: two input modes (VIN decoded via vPIC, or make/model/year) are described, which tells the agent what to supply. There is no explicit when-to-use vs. when-not, and none of the sibling tools (check_product, get_recall, search_recalls) are named as alternatives to prefer in a given situation.

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