Qualité de l'eau à La Réunion : robinet et baignade

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

Annotations already declare readOnly, idempotent, open-world, so the safety profile is covered. The description adds genuine behavioral context beyond that: the authoritative source (ARS), the data granularity (network by network vs sample by sample), the 6-month exceedance window, and the inclusion of the shark-regulation zone rule for bathing results.

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?

Scope and source are front-loaded, and the parenthetical enumerations of beaches and pools and the example questions all earn their place by anchoring the lookup. The trailing bilingual summary is slightly redundant given the French text, keeping it from a 5.

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 no output schema, the description does the necessary work of indicating what comes back (latest analysis, conformity status, parameters over limits, per-sample bathing results, permitted zones). It doesn't state what happens on ambiguous or unmatched `lieu` values or how results are structured, a minor residual gap for a read-only lookup.

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%, so baseline is 3, but the description earns a bump by explaining what each `eau` branch actually returns — tap water yields network-level compliance and germ data, bathing yields per-sample results plus permitted zones — which enriches the enum semantics beyond the schema's one-liners.

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 resource and scope: ARS-controlled tap water (network by network, latest analysis, compliance, exceedances over 6 months) and bathing water (beaches and pools, sample by sample). It never names or differentiates against close siblings such as qualite_air, coupures_eau, or restrictions_eau, so it falls 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?

Four concrete example questions ("l'eau du robinet est potable à Cilaos ?", "on peut se baigner à l'Hermitage ?") give an agent a clear sense of when this tool applies. There are no explicit exclusions or alternative routing, so it stops short of 5.

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