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 agent knows it's a safe, closed-world read operation. The description adds useful context beyond that: the results are 'indicatif' and a signed manufacturer validation takes precedence, which is not encoded in annotations. However, it does not describe the return format, any possible side effects from 'referencer', or permission requirements, so it adds only moderate value over the structured data.

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 description is front-loaded with the purpose and usage call-to-action, then packs an inventory of checks and parameter details into a single dense paragraph. Every sentence contributes, but it is quite packed; breaking the long enumeration into shorter sentences would improve readability without adding noise.

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 multiple checks and no output schema, the description does well to explain the process, action modes, and scene structure. However, it never describes what the response looks like—e.g., per-opening assigned types, validation statuses, or error indicators—which is important for an agent to interpret results. The 'indicatif' caveat helps but does not fill that gap.

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 50%—only 'scene' has a description, while 'action' has an enum but no per-value documentation. The description compensates well: it lists the fields inside 'scene' with concrete enum values for 'type' (fenetre|porte|porte_entree|baie) and 'materiau' (pvc|alu|bois), and it documents both 'action' values with their meanings and the default ('verifier'). This adds substantial meaning beyond the schema for both parameters.

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 opens with a specific verb ('REFERENCER LES MENUISERIES') and resource ('catalogue fabricants (EXE)'), then lists exactly what the tool does: assigns nearest manufacturer type, checks bounds, PMR constraints, type presence, and nomenclature coherence. It does not explicitly name sibling tools like cao_bim_fabricants or cao_bim_pose_menuiseries, so it lacks direct differentiation, but the purpose is unambiguous.

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 clearly states when to call ('Appelez quand vous devez REFERENCER...') and describes the two modes ('referencer' vs 'verifier' default), including which one attributes types. It also adds the caveat 'Indicatif — validation fabricant signee prime'. However, it does not explicitly name when not to use it or name alternative tools for adjacent tasks.

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