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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description still adds useful behavior beyond them by enumerating what is returned: phase requirements, per-element evaluation, and the list of lagging elements — valuable since there is no output schema. "Lecture seule" is redundant with the annotation and no auth/limits context is given.

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?

Two dense sentences: trigger first, then behavior, then return values, then the read-only note. Zero filler, though the trailing "Lecture seule." duplicates the annotation and slightly dilutes the front-loading.

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 two-parameter read tool with no output schema, the description covers purpose, phase vocabulary and output shape adequately. The remaining gap is the nested `scene` object, whose accepted structure (murs/boites/ouvertures/...) is only sketched in the schema and not expanded in the description.

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%, so both parameters are already documented structurally. The description repeats the phase values (esquisse, aps, apd, dce, execution) that the schema's own parameter description already lists, adding no new semantics. Baseline 3 applies.

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 pair (evaluer / valider) and a precise resource (LOD/LOI of each element of a CAD scene, checked against project phase). The topic is distinct enough from siblings like cao_bim_conformite or cao_bim_4d5d that an agent can route without opening the schema, but no sibling is named explicitly.

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 evaluer le niveau de developpement (LOD) et d'information (LOI)..." gives an explicit invocation trigger rather than an implied one. It stops short of exclusions or named alternatives, so there is no guidance on when NOT to use it versus compliance or 4D/5D tools.

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