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

Annotations already declare readOnlyHint=true and destructiveHint=false, so "Lecture seule" is partly redundant, but the description adds genuinely new behavioural context: the result is INDICATIF and the normative references (NF C 13-100/15-100) and signed CCTP prevail. That caveat materially changes how an agent should present the findings. It stops short of saying what a check returns or whether a missing transformer in the scene is an error.

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?

Front-loaded with the call trigger, then the check axes, then the caveat — good ordering with no filler sentences. Minor waste: the scene structure is stated twice, once inline in the check list and again as "scene : transformateur {...}".

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 scope, the four inspected dimensions, the indicative-status disclaimer and the read-only nature; no output schema exists so return values need not be described. The remaining gap is that it does not say what the check produces (per-axis findings/verdict) or how a missing or partial transformateur in the scene is handled.

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 a single parameter and 100% schema description coverage, the schema already documents the scene and its nested transformateur object. The description restates the same four keys ({emplacement, protection, refroidissement, acces}) and only the TR-* codes add marginal mapping value beyond the schema.

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 (VERIFIER) and resource (TRANSFORMATEUR / poste electrique) and enumerates the four check axes with stable IDs (TR-EMPLACEMENT, TR-PROTECTION, TR-REFROIDISSEMENT, TR-ACCES). An agent knows exactly what is inspected and can distinguish it from neighbouring electrical siblings such as cao_bim_tableau_electrique or cao_bim_sous_station.

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 LE TRANSFORMATEUR" gives an explicit invocation trigger rather than leaving usage implicit. It does not, however, name any alternative tool or state when NOT to use it (e.g. for the general electrical distribution or sous-station checks), which keeps it below a 5.

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