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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context beyond them: the input text is not retained ('Le texte n'est pas conservé') and the tool degrades to a bespoke letter when no template matches. It does not describe the shape of the returned match set.

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 paragraph that front-loads the core purpose before the domain list, the workflow instruction, and the privacy note. Every sentence carries information; the domain enumeration is the only slightly padded part.

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 covers what the agent needs: the input accepted (text or summary, French), the workflow position, the no-match fallback, and data-retention behavior. The only omission, the meaning of 'limit', is minor and bounded by the schema's default and range.

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 50%: 'text' is documented in the schema and the description adds that a summary is acceptable and that the content must be French. The 'limit' parameter (default 3, range 1-5) is explained nowhere, neither in schema nor description, so the description only partially compensates for the coverage gap.

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: from the text of a received French letter, find the matching situation and the Vitef reply letter. It enumerates the covered domains (bailleur, employeur, banque, assureur, vendeur, amende, organisme) and the letter types (contestation, réclamation, demande de délai, résiliation), so the agent knows exactly what class of request it handles.

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?

Gives explicit downstream sequencing: 'Utilisez ensuite get_letter puis preview_letter avec les éléments du courrier', which positions this tool as the discovery step in a three-tool chain and distinguishes it from its siblings. It also states the fallback path ('Sans modèle adapté, la lettre sur mesure est proposée'), though it never states when not to use this tool (e.g. a letter that isn't a reply scenario).

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