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

Annotations already declare readOnly/idempotent/non-destructive/open-world, so the bar is lower; the description still adds real value by naming the external data providers, the RDW field set, and confirming 'Nothing is stored'. It omits failure behavior for an invalid VIN or unknown plate, which is the main remaining gap.

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 dense sentences, front-loaded with the primary input and its constraint, followed by source/field detail and a privacy note. No filler; every clause carries 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?

With no output schema, the description does the work of naming return fields (make, model, first registration, fuel, power, APK date) — though only for the RDW path, not the VIN path. The zero-required-parameter ambiguity is the one thing an agent could still get wrong.

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 67% and the undocumented `vin` param is compensated for by the description's '17-character VIN' constraint plus the US/EU coverage caveat. It also reinforces that `country` is NL-only and `plate` is Dutch, matching the enum, though it does not explain precedence if both are passed.

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 (decode) and two concrete resources (17-character VIN, Dutch licence plate), plus the upstream data source for each. This is unmistakably distinct from the listing/price siblings, none of which touch vehicle identity resolution.

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 clear context for each input path — VIN via NHTSA vPIC with an explicit coverage caveat (US-sold and many EU makes), plate via RDW with the fields it yields. It does not state that vin and plate are alternatives and that at least one must be supplied, which matters given zero required parameters.

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