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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world) and the description is consistent with them ('Lecture seule'). Beyond the annotations it adds a real epistemic caveat — the result is indicative only and a signed ECS assessment takes precedence — which an agent needs in order to weight the output; return shape is not described.

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 trigger, then the checked criteria with their codes, then the scene shape, then two caveats — dense but well ordered with no filler. It is compact to the point of being telegraphic (abbreviations CE-COP, MEP, ECS are unexplained), a minor readability cost rather than bloat.

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 burden of describing what comes back falls on the description, and it only says the check is 'indicatif' without indicating whether the result is a per-criterion pass/fail, a score, or free text. For a nested-object check tool the input side is well served, but the return-value side is a genuine gap.

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, so the baseline is 3. The description earns an extra point by supplying the rule thresholds per field (COP >= 3,0, local >= 20 m3, hors gel), which tells the agent what values in cop/gaine_air/appoint/volume_local_m3 are actually being judged against.

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 precise verb-and-resource pair ('VERIFIER LE CHAUFFE-EAU THERMODYNAMIQUE') and enumerates the five criteria checked (COP, prise d'air, appoint, emplacement/volume, hors gel), so the tool's scope is unmistakable. It does not explicitly separate itself from near neighbors such as cao_bim_cesi or cao_bim_production_ecs, which keeps it short of a 5.

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 opening 'Appelez quand vous devez...' gives an explicit invocation trigger, and 'Indicatif — bilan ECS signe prime' tells the agent that when an authoritative ECS report exists, this tool's verdict is secondary. No named alternative tool is offered, so it falls short of full 5-level routing guidance.

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