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

Annotations already declare read-only, idempotent, non-destructive behavior, so the description only needs to add non-obvious traits. It does: null daily_price means unpublished (with an explicit instruction to say "contact for price" and never estimate), and unknown inputs return an empty page with did_you_mean rather than an error. That is genuinely useful beyond the annotations, though result envelope details overlap with the output 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 scope, then usage triggers, then edge-case handling — a logical ordering with no filler. It is denser and longer than a single-line tool needs, but each sentence (null price policy, did_you_mean fallback) carries distinct actionable 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 12-parameter, zero-required filter tool with a full output schema and annotations, the description covers selection, filters, null-price policy, and failure recovery. The only omission is how price-range and priced_only combine, which the schema silently handles well enough that an agent can call correctly.

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 the schema already carries the parameter semantics; baseline is 3. The description reinforces that model matches the site's model families and that prices are company-published daily rates, but adds no syntax or defaults 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 (find exotic/luxury rental cars from independent US rental companies) plus the exact payload the tool yields: daily rate, renting company, and citation page. It names the specific sibling fallbacks (browse_locations / browse_makes) for the unresolvable cases, so the agent can distinguish it without opening any 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 three concrete triggering questions (who rents a specific car, what is available in a state/city, what a car costs per day), which maps cleanly onto the make/model/query, state/city, and price parameters. It also states the boundary case (unknown city or make) and the two alternatives to call instead.

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