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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description is free to add behavioral value — and it does: a cap of 3 results, ranking semantics, and the fact that each result carries characteristics, a last-observed price from the brand's official shop 'when it exists', and the reasons for the pick. The one soft spot is the conditional price availability, which is disclosed but not explained (no fallback stated).

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?

Three tight sentences: what it returns, its provenance (same engine as the site quiz), and what each result contains. Front-loaded and waste-free; 'Même moteur que le quiz du site' earns its place by signalling result consistency.

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 correctly spends its space describing the return payload (characteristics, price, reasons) and caps results at 3. Given 5 enum-backed parameters with only niveau required, an agent has enough to invoke it correctly; only the interaction between budget preference and ranking is left unstated.

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% with enums and per-value descriptions for every parameter, so the schema already does the semantic work (weight ranges in grams, budget tiers, frequency). The description only restates the dimension names and does not add ranking or weighting logic beyond what the schema and annotations convey; baseline 3 applies.

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 names a specific verb and resource (recommend up to 3 padel rackets ranked by fit to a player profile) and lists the profile dimensions, so the agent knows exactly what the tool produces. It never mentions the siblings chercher_raquettes or voir_raquettes, so the boundary between recommending and searching/viewing is left to be inferred from names alone.

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?

Usage is implied rather than stated: the agent can infer that this is the tool to call when it has a player profile (niveau required, the rest optional). There is no explicit when-to-use/when-not clause and no pointer telling the agent to use chercher_raquettes for browsing or voir_raquettes for detail, which is the main gap.

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