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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description reinforces this with 'Lecture seule.' It adds valuable context beyond the annotations: the results are indicative and a signed EC2/EC5 calculation note is required, which flags the non-authoritative nature of the output.

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?

Single dense passage, front-loaded with the trigger and the numeric limits, with no filler. The telegraphic shorthand (pipes, abbreviations) slightly reduces readability but keeps it compact.

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?

Covers the inputs (nested scene structure, action semantics) and the caveat that results are indicative, which matters for a design tool. It says nothing about the return payload, and since no output schema exists that is a minor gap rather than a serious one.

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?

With schema coverage at 25%, the description compensates by defining the scene's planchers fields (nom, systeme, portee_m, epaisseur_mm, entraxe_mm), the action enum values, and how each action consumes portee_m and systeme. Units are only implied by the field names, so it is not exhaustive.

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 a specific verb (predimensionner) and resource (planchers) and enumerates the three systems with their span/thickness/spacing limits, which no sibling tool covers. An agent can tell this apart from cao_bim_structure or cao_bim_dalle without inspecting the 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?

The opening 'Appelez quand vous devez PREDIMENSIONNER LES PLANCHERS' gives an explicit trigger, and the action field distinguishes predimensionner (with portee_m, systeme) from verifier (default). No sibling tool is named as an alternative, so it stops short of full routing guidance.

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