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

Annotations already declare readOnlyHint/destructiveHint=false, so "Lecture seule" adds little. However, "Indicatif — dossier technique et norme NF P90-306 signes priment" is genuine added value: it tells the agent results are advisory and must be overridden by signed technical documentation, which no annotation conveys.

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 condition and the four domains, with zero filler sentences. It is telegraphic and code-dense, which costs a little readability, but every clause carries information.

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 single read-only parameter with no output schema, the description covers what is verified, the normative reference (NF P90-306), and the advisory caveat. It does not describe the result structure (per-domain pass/fail vs. findings), which is the main remaining 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?

With a single parameter at 100% schema coverage, the schema already documents the scene object and its nested keys. The description restates the same {etancheite, filtration, securite, plage} structure, adding only the loose mapping to check codes; no format, shape, or example of a valid scene is provided.

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 (PISCINES), then enumerates the four audited sub-domains with explicit codes (PI-ETANCHEITE, PI-FILTRATION, PI-SECURITE, PI-PLAGE). This clearly separates it from adjacent siblings like cao_bim_etancheite or cao_bim_volumes_eau, which cover only one facet.

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 LES PISCINES" gives a clear triggering condition, and the sub-domain codes indicate the scope of the check. It does not name alternatives or state when NOT to use it (e.g., versus the generic waterproofing or water-volume tools), so it falls short of a 5.

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