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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, and the description only restates this as 'Lecture seule'. It adds that the input is a CAO scene plus declared finishes, but says nothing about what is produced, formatting, or limits. With annotations carrying the safety profile, a 3 is appropriate.

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 call trigger, then the mode breakdown, then inputs, then the read-only note. Dense but efficient; no filler sentences.

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 4-parameter, nested-object tool with no output schema, the description covers the main modes and inputs but leaves the return content and the livrables parameter to the schema. Adequate, not complete.

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 all four parameters are already documented, including the action enum-ish list and the livrables object. The description usefully states what each action produces and the expected finitions shape, but omits the livrables parameter entirely, so it adds only partial value over the schema.

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 verb and resource ('produire la documentation fine de fin de chantier (DOE)') and enumerates the three output modes with their action values, so an agent knows exactly what the tool yields. It does not explicitly differentiate itself from neighbours like cao_documents or cao_nomenclatures, which is why it falls short of 5.

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?

'Appelez quand vous devez produire...' gives a clear trigger condition, and the action values let the agent pick the right sub-mode. There is no explicit 'when not to use' or named alternative tool, so it stops short of 5.

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