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

Annotations already declare readOnly and a closed-world data source, so the safety profile is covered. The description adds genuinely useful behavior: the underlying data is dealer adverts refreshed daily, results are statistical (median, interquartile range, sample size), and coverage is not limited to inventory on the platform — though it says nothing about what happens when comparable cars are too few.

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-loads the most decision-relevant fact — what comes back — before the caveats and the list_models fallback. Dense but every clause carries information; only the phrasing around the daily re-read is slightly awkward.

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 carries the return-value burden and does so by naming each returned statistic and the verdict categories. What it omits is edge-case behavior, such as insufficient comparable cars or unsupported year/make combinations, which matters for an openly-scoped query tool.

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 baseline is 3, but the description adds real meaning beyond it: make and model should be human-written strings, case and accents are ignored, and price is the switch that turns on the valuation verdict. The examples ("SEAT", "León", "Clase C") reinforce the expected format better than the schema's generic examples.

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 concrete resource and output: market price of a used car in Spain, with median, p25-p75 range, sample count, and an expensive/fair/cheap verdict. Scope is bounded ('in Spain') and the data source ('adverts of thousands of dealers, read again every day') makes it unmistakably distinct from a listing search or a province roll-up.

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 the trigger for the optional price parameter ('With an asking price it also says whether that price is expensive, fair or cheap') and routes to list_models when spelling is uncertain, plus clarifies it works for cars not listed with the site. It does not, however, say when to prefer this over province_market or search_cars, which are close neighbours.

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