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

Annotations declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, and the description is consistent with that safety profile. It adds real behavioral value beyond the annotations: the fiche is returned as full HTML inside the response, not as a file, URL or PDF, and it operates on a local folder with no SaaS portal access. It stops short of covering auth or persistence/overwrite behavior, so not a 5.

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?

Four tight sentences, front-loaded with the usage trigger and immediately followed by the sibling contrast and the return/format disclosure. The final fragment 'Dossier local — pas d'accès au portail SaaS' is terse but earns its place as an environment constraint.

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?

For a 15-parameter tool with no output schema, the description supplies the missing pieces an agent would otherwise lack: the delivery format (HTML in the response, not a file/URL/PDF) and the execution environment (local dossier, no SaaS portal). Combined with 100% schema coverage this is nearly complete, though it says nothing about what happens if a fiche with the same reference already exists.

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 description coverage is 100% across all 15 parameters, including format hints ('AAAA-MM-JJ'), defaults ('par défaut, la date du jour') and layout semantics ('bloc fenêtre poussé À DROITE'). The description contributes no additional parameter guidance at all, so the baseline 3 is correct — the schema is doing all the work.

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?

Names the artifact (fiche mission/chantier, app Missions) and frames it with a specific verb-adjacent action: the scoping step an artisan does BEFORE an intervention. It explicitly separates itself from the sibling compte_rendu_chantier ('rend compte APRÈS'), so an agent can route between the two without reading 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?

Opens with 'QUAND un artisan prépare une intervention ou un chantier — le cadrage AVANT d'y aller' — an explicit when-to-use trigger — and names the contrasting alternative (compte_rendu_chantier, used after). It also excludes a whole environment ('pas d'accès au portail SaaS'). 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.