cao_pdf

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

No annotations are provided in this context, so the description carries the behavioral disclosure burden. It does disclose a significant behavior — the sheet embeds an orange alert banner when issues remain — and notes the return format. However, it does not disclose output size, processing latency, or error behavior. Given that annotations are absent, the description does a decent but not exhaustive job, warranting a 3.

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 compact and front-loaded with the key usage context, then the prerequisite, then the output. The 'IMPORTANT' warning is appropriately placed. It loses one point because the 'Same scene as cao_generer_dxf' note is slightly buried at the end, and the sentence about the alert banner could be more prominent.

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 tool with 12 parameters, almost all documented in the schema, and no output schema, the description covers the essential context: when to use, what it produces, the critical prerequisite, and the return shape. It could add a note about what 'alertes' vs 'alertes_ok' mean or mention that the MEP plan is optional, but the description is largely complete for an agent to select and invoke it correctly.

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?

The schema description coverage is 100%, with each parameter documented in detail (e.g., murs, boites, reseaux, toitures, plomberie, decoration, ouvertures, electricite all have descriptions). The tool description itself adds almost no parameter-level information beyond the schema, which is acceptable given the high coverage. Baseline 3 is appropriate because the schema does the heavy lifting.

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 specific verb ('Generate a professional TECHNICAL SHEET'), a precise resource ('from a CAO scene'), and enumerates the deliverables (top view, elevations, shaded axonometric, optional MEP plan). It clearly differentiates from siblings like cao_generer_dxf and cao_verifier by naming them and describing the handover-to-client context.

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 description explicitly says when to use this tool ('WHEN the design must be HANDED OVER to a client, an architect or a planning office'), gives a mandatory precondition ('call cao_verifier FIRST'), and names the sibling alternative ('Same scene as cao_generer_dxf'). This is explicit when-to-use guidance with a named alternative.

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