Rechercher des produits

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

Annotations only declare readOnlyHint and openWorldHint, so the description carries real weight and does add value by disclosing the exact return payload — including the price-per-unit field and the cart-ready id — which is critical with no output schema. What's missing is any mention of result limits, pagination, or empty-result behavior for a live external catalog.

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?

Two sentences, zero filler. Scope constraint is front-loaded and the return-value clause directly sets up the next call rather than padding the description.

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 single-parameter read tool with no output schema, the description covers purpose, store dependency, and return fields — enough to call it correctly the first time. It stops short of explaining pagination or what happens when the selected store has no catalog loaded.

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% and the schema's own description already gives an example query ("lait demi-écrémé bio"), so the schema does the heavy lifting. The tool description adds nothing about the query parameter itself (no matching behavior, no accent/plural handling), so baseline 3 is correct.

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 and resource ("Recherche des produits dans le catalogue Leclerc Drive") plus the scope constraint ("du magasin sélectionné") and even enumerates what comes back (libellé, prix, prix au kilo/litre, disponibilité, id). Sibling names confirm the distinction: all other tools are cart/store operations, so an agent can immediately tell this is the discovery step.

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 phrase "du magasin sélectionné" signals the prerequisite that a store must be chosen first (find_stores/set_store) and that results vary by store. It also links forward in the workflow by noting the returned id is what add_to_cart needs. No explicit when-not or alternative is named, so it falls short of a 5.

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