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 goes further by disclosing the calculation model (window area assigned per room, default transmission 0,7, sky factor 0,55 reduced by declared masks) and the important caveat that the result is indicative rather than regulatory. It stops short of describing the output shape, which keeps it at 4.

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?

It is one dense block rather than a bulleted list, but it is front-loaded with the invocation condition and each clause (thresholds, computation chain, caveat, read-only) carries information. Slightly heavy nesting of parentheticals costs it a point.

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?

Input semantics and the calculation basis are well covered, but there is no output schema and the description never says what comes back (per-room FLJ value, pass/fail versus the two thresholds, orientation advice listing). For a single-object-input analysis tool the agent is left guessing the return shape.

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 100 % and the single 'scene' object is already documented, but the description adds real meaning for the nested fields: pieces[i].fenetres is a list of window indices, masques carry orientation + angle_deg, and transmission defaults to 0,7 when omitted. That goes beyond the schema text for a nested-object parameter.

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 ('verifier l'ECLAIRAGE NATUREL (FLJ) d'une scene') and pins it with concrete thresholds (1/6 surface vitree, FLJ >= 2 %). The sibling cao_bim_eclairage_artificiel covers the artificial-lighting case, and the word 'naturel' plus the EN 17037 / R. 4223 references make the boundary 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?

'Appelez quand vous devez verifier...' gives an explicit invocation trigger, and 'Indicatif — le FLJ reglementaire exige une simulation dediee' tells the agent when the result is not authoritative. It does not name a concrete alternative tool, so it falls short of the 5 bar.

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