journal_kilometrique

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

There are no annotations, so the description carries the behavioral burden. It does disclose a mutating call via 'POST' and notes that `taux_km` is optional. However, it does not explain what the generated document looks like, whether indemnities are actually computed from `taux_km`, or what side effects occur. The schema's note that the official rate is 'PAS calculé ici' is useful but lives in structured data rather than the tool description.

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 compact and information-dense: trigger condition, purpose, endpoint, and key request structure are all packed into one short block. The telegraphic style is slightly awkward, especially the uppercase 'QUAND', but every element contributes to the agent's ability to invoke the tool.

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 annotations and no output schema, an agent still has to infer important end-to-end details, such as what happens when `taux_km` is omitted and how the 'indemnités' are produced. The parameters themselves are well covered by the schema, but the description does not fully explain the result of the POST or whether `trajets` is semantically required despite the empty `required` list.

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%, so the baseline is 3. The description adds meaningful value by specifying the nested `trajets[]` shape as `{date, depart, arrivee, km, motif}`, which the schema's `items` description does not provide as concrete field names. It also reaffirms `taux_km` as optional, though that is already implied by the empty `required` list.

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 names the concrete resource (`journal-kilometrique`), gives the endpoint (`POST /api/v1/documents/journal-kilometrique`), and states the deliverable (`Journal kilométrique + indemnités`). It lacks an explicit imperative verb like 'crée' or 'génère', but the HTTP verb and resource make the action inferable. It does not explicitly differentiate itself from sibling tools such as `note_frais`, though the endpoint and wording make the scope reasonably clear.

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 opens with an explicit trigger condition: 'QUAND les déplacements doivent être justifiés (barème kilométrique)'. This tells the agent when to use the tool. It does not provide when-not conditions or explicitly name alternatives, but the sibling list contains no directly competing mileage-log tool, so the context is clear enough.

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