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

Annotations already establish read-only, non-destructive, closed-world behavior. The description adds real value beyond that: it enumerates what the tool outputs (quantities, norms, control points, the consolidated dossier with reserves, manufacturer nomenclature, 4D planning, completeness verdict) and warns 'Indicatif — plans signes et visa BE obligatoires,' signalling the result is non-authoritative. 'Lecture seule' merely repeats readOnlyHint, but the rest is substantive.

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?

The trigger condition is front-loaded and the dense, em-dash-separated clauses are almost all substantive, but it is a single sprawling run-on sentence that would scan better split into purpose / actions / output sections.

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 complex tool with a nested scene object, no output schema and only two parameters, the description does well: it spells out the actionable payload and the indicative-authority caveat. Minor gap is the absence of scene-quality prerequisites, but the schema covers the scene content.

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 baseline is 3. The description goes beyond the schema by detailing what each action produces (e.g. verifier checks for containers outside lots, missing gros oeuvre, menuiseries without manufacturer; dossier assembles lots + reserves + nomenclature + 4D planning + verdict) and describing the 9-lot subdivision of the scene.

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 very specific verb+resource: producing the multi-lot EXE package with a detailed breakdown (9 lots, quantities, DTU/NF norms, control points, tolerances). An agent can immediately grasp the result. However, it never distinguishes itself from overlapping siblings like cao_bim_lots, cao_bim_dossier_complet, cao_bim_cctp or cao_bim_dtu, so it falls short of the top score.

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 'Appelez quand vous devez produire le DOSSIER EXE MULTI-LOTS', giving clear trigger context, and explains the three action modes (verifier as default, lots, dossier). Missing explicit 'when not' or named alternatives against the many related BIM siblings, so no upside to a 5.

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