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

Beyond the safety annotations, it discloses the text output and its per-offer fields, default and maximum result counts, absence of pagination, explicit errors for unknown or empty categories, and the lack of account or API-key requirements. « Lecture seule » repeats the annotations but is consistent with them, while the remaining operational detail is substantial.

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 front-loaded and progresses logically from purpose to tool routing, output, errors, and access requirements, with no filler. It is somewhat dense and repeats schema or annotation facts such as the limits and read-only status, so it is not perfectly economical.

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 simple two-parameter read tool, it covers selection criteria, sibling alternatives, result shape and fields, result limits, pagination, error behavior, and authentication. Because there is no output schema, the explicit text-output description and field list are especially valuable, and no material invocation detail appears missing.

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?

The schema already fully documents categorie and limite, including case handling, examples, bounds, and the default, so parts of the description repeat structured information. It still adds useful semantics through the single-category scope, explicit invalid-or-empty-category failure, and confirmation that the result cap cannot be extended through pagination.

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 opening sentence gives a precise verb, resource, and scope: listing verified referral offers from a single category in a named directory. The routing sentence further distinguishes it from rechercher_offres, detail_offre, meilleures_offres, and lister_categories.

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?

It explicitly says to use the tool for product-type searches without a named brand and supplies concrete examples such as « une banque en ligne ». It also gives alternatives for brand searches, the cross-category monthly selection, and discovery of exact category names, making both positive and negative selection conditions clear.

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