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

No annotations are present, so the description carries the burden of behavioral disclosure. It reveals valuable behavior: coverage represents the proportion of search terms contained in each product, and reference_exacte indicates whether the search matched a product reference exactly. It also documents the side-effect of filters on reference_exacte. However, it does not describe the full response shape, pagination behavior, or error conditions, leaving meaningful gaps.

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?

The description is two short, front-loaded sentences with no filler. The first sentence establishes the core purpose, and the second explains the distinctive return semantics. Every word contributes, making it appropriately sized for a search tool.

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 tool with nested filters, pagination, and no output schema, the description is adequate but not complete. It explains the key response fields but omits the full result structure, pagination defaults and limits, and any guidance on how store_id affects pricing context. These omissions are more significant because there are no annotations or output schema to fill the gaps.

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 the baseline is 3. The description adds semantic meaning beyond the schema: it explains how coverage is computed, what reference_exacte means, and that using filters forces reference_exacte to always be false. This extra context goes beyond what the schema already documents.

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 clearly states the tool's purpose: 'Recherche de produits dans le catalogue' – a specific verb and resource. It goes beyond the name by explaining the coverage field and reference_exacte flag, which helps distinguish it from sibling tools like get_product and get_recommendations, though it does not explicitly name those alternatives.

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 description implies this tool is for searching products by term or exact reference, but it does not explicitly say when to use it over get_product, check_stock, or get_recommendations. It does provide useful usage context, especially the warning that using filters disables exact-reference matching, but there is no when-not-to-use guidance.

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