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

With no annotations, the description carries the behavioral burden and does so well: it discloses that the output is full HTML returned inline (no file, URL, or PDF) and explicitly states that no reimbursement is triggered, which is a critical side-effect disclaimer for a tool named around reimbursement. It stops short of covering auth/permission requirements, so it is not fully complete.

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?

Dense but front-loaded, leading with the conditional trigger before the app name, output format, side-effect disclaimer, and payload shape. Every clause carries information, though the single long sentence is somewhat crowded rather than crisply segmented.

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 properly explains the return value (full HTML in the response, no file/URL/PDF) and the side-effect status (no reimbursement triggered). Combined with the parameter payload hint, an agent has everything needed to call it 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 already 100%, but the description adds genuine value beyond it: the nested lignes items are typed only as a bare 'object' in the schema, while the description enumerates the expected fields ({date, libelle, montant, mission, justificatif}), going beyond the schema's own prose of date/nature/montant TTC/justificatif.

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 resource (generating a note de frais) and immediately distinguishes itself from the sibling journal_kilometrique by contrasting receipts-based actual expenses with the mileage scale. An agent can tell what this tool does and does not do 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?

Opens with an explicit 'QUAND' trigger (expenses to be reimbursed or justified) and names the alternative tool along with the exact condition that selects it (dépenses réelles sur justificatif vs barème kilométrique). Both the when and the when-not-to-use are given.

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