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

Annotations already establish readOnlyHint=true and destructiveHint=false, so the bar is lower, yet the description adds meaningful context: output is returned as full HTML in the response (no file, URL or PDF) and no reimbursement workflow is triggered. The only gap is pagination/size behavior, which for a read-only draft tool is minor.

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?

Front-loaded with the trigger condition, then the alternative, then behavior, then field shape — every clause carries information. It is dense to the point of being terse, but not padded.

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?

There is no output schema, so the description appropriately discloses the return format (HTML in the response, no artifact produced). With annotations covering safety and the schema plus description covering all six parameters, an agent has what it needs to call this correctly.

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 baseline is 3, but the nested lignes items object has no defined properties in the schema, and the description supplies them ("lignes[] = {date, libelle, montant, mission, justificatif}"). That adds genuine meaning beyond the structured fields, though it slightly diverges from the schema's wording ("nature", "montant TTC").

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 action and artifact: drafting an expense report ("Note de frais"), and explicitly distinguishes it from the sibling journal_kilometrique by contrasting "dépenses réelles sur justificatif" with "barème kilométrique". An agent can pick this 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 definition leads with "QUAND ..." giving the triggering condition (expenses to be reimbursed or justified) and names the alternative sibling plus the rule that selects between them. Nothing is left to inference.

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