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

With no annotations, the description carries the burden and discloses the key behavioral trait: the log is returned as full HTML in the response — no file, no URL, no PDF. It also notes the default taux_km behavior. It does not state auth/permission needs, persistence, or side effects, so it is strong but not exhaustive.

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 well ordered: routing condition first, then purpose, then output contract, then parameter notes. There is minor redundancy in "ni fichier, ni URL, ni PDF," but every sentence carries information and nothing is buried.

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 and no annotations, the description supplies the most needed missing piece (return format = HTML in the response) along with params and the sibling alternative. It stops short of describing what the HTML contains or whether anything is stored server-side.

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, but the description adds meaning the schema lacks: the trajets[] element shape {date, depart, arrivee, km, motif} (the schema only types items as a bare object) and the optionality/default of taux_km. This goes beyond the structured fields.

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 states a specific verb and resource — generates a mileage log plus indemnities ("Journal kilométrique + indemnités") — and explicitly names the sibling it is not ("pour des frais réels sur justificatif, c'est note_frais"). An agent can distinguish this from note_frais without opening either 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?

It front-loads the trigger condition ("QUAND les déplacements doivent être justifiés au BARÈME kilométrique") and gives the explicit exclusion + alternative (frais réels sur justificatif → note_frais). Both when-to-use and when-not-to-use are covered with no inference required.

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