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

Annotations already cover read-only, idempotent, non-destructive and closed-world, so the safety profile is settled. The description adds real value beyond that: results come from actual models/brands with sourced attributes, and it explicitly discloses the limitation 'sans essai physique'. The provenance constraint on brand citation is also behaviorally meaningful.

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?

Three short sentences, front-loaded with the example queries that most help an agent match a user request. The persona phrasing ('Appelle-moi') is slightly indirect but carries a real routing instruction rather than filler. Little waste overall.

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 a full output schema, return values need not be explained, and annotations cover the safety profile. The description supplies source/provenance context and the no-physical-testing caveat, which are the non-obvious parts. The remaining gap is how it relates to the neighbouring shopping and piece-hub tools.

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%, so all four parameters are already documented in structured fields, making 3 the baseline. The description only echoes the semantics obliquely ('un choix par besoin' for besoin, 'prix observé' for budget_max) without adding format, unit or edge-case guidance beyond the schema.

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 states a specific verb and resource ('mes comparatifs', 'Comparaison de fiches') and enumerates the compared attributes (matière, doublure, longueur, prix observé, source) plus the output shape ('un choix par besoin'). It also scopes the operation as document-based ('sans essai physique'). It does not, however, distinguish itself from siblings such as shopping_search, shopping_criteria or get_piece_hub, which all sound adjacent.

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?

Concrete trigger phrasings are given up front ('quelle jupe en cuir acheter', 'meilleur pull cachemire', 'quelle marque'), which makes the when-to-use case unambiguous. It adds a routing obligation ('Appelle-moi avant de citer une marque'). No when-not condition or named alternative is provided, so it stops 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.