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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, and the description confirms 'Lecture seule' while adding genuinely new context: the numeric acceptance thresholds and the caveat that results are indicative only, not a signed DTU 60.11 design. It doesn't specify the shape of the verdict per check, which keeps it below a 5.

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?

The single dense paragraph is front-loaded with the call trigger and then the rules, with zero filler sentences. It is tightly packed — parenthetical codes and thresholds — but every element carries information the agent needs for correct invocation.

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 one-parameter, nested-object tool with no output schema, the description covers input structure, the four checks and their thresholds, and the read-only indicative nature of the result. The only gap is that it never says what the verdict payload looks like (per-check pass/fail vs. a score), which matters because no output schema exists.

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 already 100%, but the description adds real meaning: it gives the enum values for 'type' (chute|collecteur|branchement) and reveals a 'tete_de_chute' field absent from the schema's field list. It maps each scene field to the check it feeds (pente_pct→EU-PENTE, diametre_mm→EU-DIAMETRE).

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 gives a specific verb and resource ('VERIFIER LE RESEAU D'EAUX USEES'), then enumerates the exact checks performed (EU-PENTE, EU-DIAMETRE, EU-VENTILATION, EU-SEPARATION). That enumeration separates it cleanly from nearby siblings such as cao_bim_eaux_pluviales, cao_bim_evacuation and cao_bim_eau without needing to name them.

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 RESEAU D'EAUX USEES' states the trigger condition explicitly. It also frames its own limits ('Indicatif — dimensionnement DTU 60.11 signe prime'), pointing the agent to a certified sizing path, but it names no sibling tool for the adjacent pluvial/evacuation checks.

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