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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so 'Lecture seule' merely restates structured data. The one genuine addition is the 'Indicatif — DTU plomberie et CCTP signes priment' caveat, which warns that the check result is advisory and normative documents take precedence. Nothing is said about what a check returns or how findings are reported.

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?

A single compact paragraph, front-loaded with the trigger and then the parameter shape and the caveat. There is minor redundancy in restating the scene structure that already appears in the schema, but no wasted preamble.

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?

For a read-only verification tool with no output schema, the definition conveys what is checked and that results are indicative, which is the essential minimum. It does not indicate what the agent receives back (list of nonconformities, per-aspect status?) or how the four FE-* codes surface in the response, leaving a meaningful 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?

There is a single parameter whose schema description already covers 100% of the surface, and the description repeats the same 'filtration_eau {emplacement, raccordement, entretien, controle}' structure verbatim. The four sub-keys are meaningful but are not explained beyond their names, so no real semantic value is added over 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?

The description states a specific verb ('VERIFIER LA FILTRATION / TRAITEMENT D'EAU') and enumerates the four sub-checks with their codes (FE-EMPLACEMENT, FE-RACCORDEMENT, FE-ENTRETIEN, FE-CONTROLE). That is enough to separate it from nearby siblings such as cao_bim_eau, cao_bim_eau_froide or cao_bim_adoucisseur, though it never names those siblings explicitly.

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 trigger condition, and the closing 'Indicatif — DTU plomberie et CCTP signes priment' tells the agent how much weight to give the result. There is no explicit when-not guidance or named alternative tool, 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.