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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered; the description adds genuinely non-obvious traits: deterministic rule-based output, that it explains each step and the typical dealer gap, that prices are never converted from PLN, and that nothing is stored. It stops short of describing latency, rate limits, or output structure in detail, which keeps it off 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?

Four compact sentences, front-loaded with what the tool returns before caveats about currency and storage. Every clause carries information an agent would otherwise have to guess, with no filler.

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 7 parameters, a nested object, and no output schema, the description does the necessary work of conveying the return shape (low/mid/high EUR plus step-by-step explanation) and the currency invariant. The remaining gap is that requiredness of newPrice and the vehicle-object fields is only implied, not stated.

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 only 57% and one parameter (km) has no description at all, but the description compensates by tying mileage, condition, new-when-new price, and identity routes together and clarifying that the vehicle object serves as overrides. Only lang and the exact composition of the nested vehicle object are left to 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+resource: a rule-based low/mid/high EUR price range estimated from VIN, Dutch plate, or make/model/year plus mileage and condition. It also draws the boundary against sibling decode_vehicle by framing the tool as an estimator that consumes decoded identity, and against a valuation by saying 'Not a valuation'.

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 useful framing ('Not a valuation', the dealer gap, always EUR) and enumerates accepted input routes (VIN, plate, or vehicle object), so a competent agent can infer when to call it. But it never explicitly says when to prefer it over decode_vehicle or when newPrice is mandatory versus optional, leaving routing to inference.

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