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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so safety is covered. The description adds valuable behavioral context beyond that: results are ranked by ingredient overlap and each result includes both used and to-buy ingredients, which tells the agent what the call produces.

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?

A single front-loaded sentence that packs the action, ranking rule, and return content with no filler. Slightly dense, but every clause earns its place.

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 read-only search tool with no output schema, the description covers both the retrieval logic and the shape of each result (used vs to-buy ingredients), which is what an agent needs to call and interpret it. Missing only alternative-routing guidance.

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 description coverage is 100% with clean enum/range docs for all 7 parameters, so the schema carries the semantics. The description adds no additional parameter detail (e.g., ranking sensitivity or how ingredient matching works), leaving the baseline 3.

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 ('Trouve') and resource ('recettes') with a distinguishing ranking criterion: recipes that use the most of the ingredients already on hand. It differentiates implicitly from a generic search by emphasizing pantry-maximizing results, though it does not name sibling 'chercher_recettes'.

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?

The scope ('ce que l'on a', placard/réfrigérateur) implies the use case of cooking from existing supplies, but there is no explicit when-to-use framing, no prerequisites, and no routing versus 'chercher_recettes' or 'idees_session'.

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