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

With no annotations, the description carries the full burden and largely succeeds: it names the return keys {scene, rapport, controles, metres}, states conflits:true adds clash detection and studio:true opens a 4K video studio plus VR tour URLs. It omits permissions, rate limits, and failure behavior.

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?

One dense sentence chain, but the trigger condition is front-loaded and every clause carries information (elements, GlobalId, return keys, flag effects). It is heavy for a single paragraph but not padded.

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?

With no output schema, the description supplies the return structure and flag-dependent side effects, which is what an agent needs to pick this tool and set flags. Missing only auth/error context, which is a minor gap for an import tool.

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 already 100%, but the description adds real meaning on top: studio:true 'opens the 4K video studio and the VR tour', conflits:true 'adds clashes', metres:true equals quantities, and scene is the reusable object. This goes beyond the schema's one-line parameter descriptions.

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 and resource — converting IFC text into a CAO scene — and enumerates the produced elements (walls, doors, windows, stair flights, railings, rooms, furniture, roof) and the GlobalId retention. This clearly distinguishes it from siblings like cao_generer_ifc or cao_valider_ifc, which do not import-and-convert with this element coverage.

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 'WHEN an architect sends an IFC ... and you must check it with our rules' trigger gives an explicit usage context, and it says to reuse `scene` with other cao_* tools. It stops short of naming when NOT to use it versus cao_generer_ifc or cao_valider_ifc.

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