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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the bar is lower; the description adds real value by enumerating what comes back (defect, safety risk, remedy, manufacturer notes, affected vehicles). With no output schema, that return-shape disclosure is what an agent needs to judge usefulness, though pagination/not-found behavior is unaddressed.

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?

Two sentences, zero filler, with the action and identifier front-loaded ahead of the conditional usage note and the return payload.

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?

Single fully-documented required parameter, annotations covering operation safety, and an inline enumeration of return fields standing in for the absent output schema. Nothing required to call it correctly is missing.

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% and already carries the example, so the baseline is 3; the description nudges higher by explaining where the value comes from ('often printed on a recall letter'), which helps an agent recognize a usable campaign number in a user's message.

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 (look up) and resource (one NHTSA recall) scoped to a single campaign number, with a concrete example. The 'one ... by its campaign number' phrasing cleanly separates it from the search_* recall siblings that return sets.

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?

Explicit trigger condition: 'Use when the user has a recall notice or campaign number.' This gives a clear when-to-use but does not name the alternative to pick when the user lacks a campaign number (e.g. get_vehicle_recalls or search_* recalls).

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