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

Annotations already declare readOnlyHint=true and openWorldHint=false. The description adds useful context beyond them: it names the returned content (signification, action attendue, faut-il un avoir) and discloses the data source/auth condition ('Sans clé, données du site MaFactureOK').

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?

One dense sentence, front-loaded on the action, with the code families and output content packed efficiently. It is long but every clause (code families, output fields, no-key note) carries information.

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 must convey what comes back, and it does (meaning, expected action, whether a credit note is needed). Combined with the readOnly annotation and the data-source note, an agent has enough to call it correctly; only explicit alternative-routing guidance is 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?

Schema description coverage is 100% and the single 'code' parameter already carries examples (REJ_SEMAN, BR-CO-15). The description's longer code enumeration reinforces the accepted format but adds little beyond the schema, so baseline 3 applies.

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 ('Traduit en clair') and a precise resource (rejection reasons / validation rules for electronic invoices), with concrete code families (AFNOR XP Z12-012, EN 16931, BR-CO-15). An agent can distinguish this explanatory tool from the sibling validators (valider_facture, verifier_tva) without opening the schema.

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 makes the usage context inferable ('un motif de rejet … tel que reçu') but never states when to call this instead of valider_facture or verifier_tiers, nor does it exclude any cases. Adequate implied usage, no explicit routing.

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