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

Annotations already declare readOnly/idempotent/non-destructive/openWorld=false, yet the description adds substantial value: it enumerates the three possible verdicts (autorise, interdit, a_verifier), states that a sourced explanation and article URL accompany the result, and flags the editorial/not-medical-advice nature. This is real behavioral disclosure beyond structured fields.

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 core question is front-loaded in the first clause, followed by examples, then the return semantics and caveat. It's dense but every part earns its place; the example list is slightly long but aids disambiguation.

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 well by naming the verdict vocabulary and the accompanying source/URL. The product-vs-ingredient caveat closes the main ambiguity for a single-param lookup 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% and the schema itself documents the single 'ingredient' parameter with French examples. The description's example list mirrors rather than extends the schema, so it adds little semantic depth beyond the baseline.

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 precise verb+resource ('répond à X contient-il du gluten') scoped to ingredients/common foods, and lists representative examples (blé, semoule, sauce soja, avoine…). An agent can distinguish this from get_product or search_products, which target specific products rather than ingredient-level verdicts.

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?

Clearly frames the context (ingredient or common food, not a specific product) and warns 'pour un produit précis, l'étiquette fait foi', implicitly steering product queries elsewhere. It doesn't explicitly name a sibling tool, but the scope boundary is unambiguous.

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