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

Annotations already declare readOnlyHint/openWorldHint/destructiveHint, and the description usefully goes beyond them: it discloses the calculation basis (120 L/day/occupant, -20% with efficient fixtures, 60 L/m2/an watering), that a garden over 100 m2 without a cistern is flagged, that a sector meter and repaired leaks are required, and that results are indicative only. The bare 'Lecture seule' merely repeats readOnlyHint, but the substantive disclosure is real.

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 trigger is front-loaded and every clause carries information (rates, thresholds, scene fields). It is dense and hyphen-heavy, with a couple of run-on clauses that slow parsing, but nothing is padding.

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?

With one parameter, no output schema and annotations covering safety, the description supplies what is actually needed: what is computed, on what assumptions, and that the answer is indicative. It could say more about what the response contains (annual figure, savings, reuse volume, flagged issues), which is the 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?

Schema coverage is 100% and the single scene parameter is described, so the baseline is 3. The description earns a notch more by attaching meaning to fields the schema only lists: what jardin_m2 and citerne_m3 are used for and the {declaree, reparee} structure of fuites. Still, it does not give units, defaults or required/optional status for occupants or appareils_economes.

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 names a specific verb and resource: verifying the drinking-water consumption of a dwelling, with annual estimate, rainwater reuse and garden/cistern checks. It is clearly narrower than generic siblings, but it never names or distinguishes itself from near-neighbours such as cao_bim_eau_froide, cao_bim_eaux_pluviales or cao_bim_aev, so an agent cannot route between them from this text alone.

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 la CONSOMMATION D'EAU POTABLE d'un logement' gives an explicit trigger condition. It states no exclusions or alternative tools however, and the closing 'Indicatif — diagnostic eau reel prime' warns the output is advisory but does not say which tool to use instead.

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