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

Annotations already cover safety (readOnly, idempotent, non-destructive, openWorld), so the bar is lower. The description still adds real value: the field list returned per recall, the 25-item cap, and the interpretive caveat that an empty result is not a safety guarantee.

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?

Four tight sentences, each carrying distinct information: trigger, inputs, return shape, and scope limitation. The use case is front-loaded before the caveats.

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 an output schema present, the description need not enumerate return values, yet it summarizes them anyway. Annotations cover safety, the schema covers inputs, and the description covers scope limits — nothing an agent needs 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 description coverage is 100%, so all four parameters are already documented, including the default of 10 and newest-first ordering. The description restates year/make/model and the limit cap but adds no syntax or format detail 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?

States a specific verb and resource (list recalls) scoped to a car model, with a concrete example query. It is clearly distinguishable from siblings like decode_vin and get_vehicle_report, which answer different questions.

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?

Opens with an explicit trigger condition ('when the user asks about recalls for a car model') and gives a sample phrasing. It also states the negative case — recalls are keyed by year/make/model, not VIN — and routes VIN-level lookups to nhtsa.gov/recalls instead.

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