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

Annotations already cover readOnly, idempotent, non-destructive, and closed-world, so the safety bar is low. The description still adds meaningful context beyond them: the 10-result cap, the absence of bulk export/pagination, and the exclusion of private dealer/consumer data. It does not spell out auth requirements or error behavior, keeping it short of a 5.

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?

Purpose is front-loaded, followed by the filter inventory, the routing rule to the sibling, and the return/limitation notes. The middle filter enumeration is long but informative for a 27-param tool. No wasted sentences, though the filter list is dense.

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 no-output-schema, 27-param search tool, the description covers return shape (max 10 public vehicles, canonical URLs, structured specs, provenance), privacy constraints, result cap, and the alternative tool. The main gap is per-parameter meaning for the low-coverage schema, but overall it is complete enough to invoke 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?

With 27 parameters and only 37% schema description coverage, the description carries a compensation burden. It enumerates the filter categories (vehicle type, make/model, condition, price, year, berths, travel seats, transmission, fuel, layout/bed, dimensions, licence/weight, payload, mileage, features, dealer, postcode/radius) which maps broadly to the params, but adds little per-parameter semantics beyond the schema's own hints. Baseline 3 for the low-coverage case.

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 (search) and resource (public UK caravan/motorhome/campervan listings), and explicitly scopes it to 'structured buyer filters'. It distinguishes itself from the sibling find_matching_vehicles by naming it and describing the division of labor. An agent can tell it apart from get_listing or find_matching_vehicles without opening a 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?

It gives an explicit rule for when to use this tool ('hard limits exactly as supplied') and when to use the alternative ('for fuzzy priorities and trade-offs use find_matching_vehicles'). This is exactly the when/when-not/alternative guidance the rubric rewards.

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