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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, yet the description adds value beyond them: cost ('Free'), result semantics (canonical names, years, match kind), and the cross-tool contract that the returned vehicle id is passed as `vehicle` to the image and 3D tools. That chaining information is behavior an agent cannot infer from annotations or schema.

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-loaded with purpose and catalog size, then return contract, then use cases and alternative; the 'Free' opener is short and materially useful given the get_pricing sibling. It is one long compound sentence with nested parentheticals, which is dense but nearly every clause carries routing or chaining information.

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 search tool with an output schema and full annotation coverage, the description supplies everything still needed to call it correctly: what matches, how typos are handled, what the ids mean, and where to route when the search shouldn't be used. Nothing material 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%, so query, year and limit including ranges, defaults and examples are already documented; the baseline of 3 applies. The description adds a little meaning by tying the year parameter to receiving a single stable id ('id when the query names one year'), but it leaves limit and year restriction behavior to the schema rather than enriching them.

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 (browse the open vehicle catalog by make and/or model) plus concrete scope (1,608 makes, 42,330 models, 1990-2027) and typo tolerance. It explicitly distinguishes itself from sibling resolve_vehicle and positions itself as the feeder for the image and 3D tools, so an agent can classify it without opening the schema.

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 named use cases (list a make's models, check which years exist, let the human choose between similar models) and an explicit alternative with the selecting condition: when the car is already known, use resolve_vehicle instead. Both the when and the when-not are stated.

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