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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered; the description adds real context beyond that: what the conversion preserves (GlobalId/ifc_guid per element), what each flag produces (conflits adds clashes, studio opens a 4K video studio and VR tour), and the return payload. One minor tension: 'studio:true opens the ... video studio' implies a side effect for a tool annotated read-only, though it is likely just URL generation.

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 WHEN-condition and the conversion outcome are front-loaded, and every clause carries information. It is dense — long em-dash chains mixing French domain terms (rapport, controles, metres) with the English framing — but no sentence is filler.

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?

There is no output schema, so the description takes on return-value disclosure and does it well: it names the four returned keys and explains two of them (controles = cao_verifier audit, metres = quantities). Combined with the element list, flag behavior, and the reuse instruction, an agent has everything needed to call and consume it.

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 description coverage is 100%, so the baseline is 3. The description still adds meaning by tying the flags to concrete outputs (metres = quantities, conflits = clashes, studio = video studio + VR tour) and by specifying the accepted IFC dialects (IFC2X3 or IFC4). The `controler` flag is only indirectly implied by 'check it with our rules'.

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 ('converts the IFC text into a CAO scene') and enumerates the extracted element types (walls, doors/windows hosted on walls, stair flights, railings, named rooms, furniture, roof). An agent can separate it from siblings like cao_valider_ifc, cao_conflits_ifc or cao_generer_ifc, which imply validate/clash-check/generate rather than import-and-convert.

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?

Front-loads a clear trigger: 'WHEN an architect sends an IFC ... and you must check it with our rules'. It also routes onward usage ('Reuse `scene` with every other cao_* tool'), which is useful sequencing guidance. It stops short of naming which sibling to pick when the goal is pure validation or clash-only checking.

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