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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so safety is settled; the description then adds genuinely useful context beyond them: the source is prefect decrees, the answer should cite the article, and location-dependent rules may fall outside what the tool knows. That last point is an important honesty constraint on a legal-reference tool that the annotations alone would not convey.

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 scope enumeration is front-loaded, followed by the caveat and then example queries — a sensible order with no filler. The first sentence is dense (a long parenthetical list), but every element maps to a real answer category the agent may need.

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 carries the burden of explaining what comes back, and it does so by enumerating the answer categories (closures, hours, sizes, quotas, prohibitions, lagoons) plus the citing requirement. The only residual gap is that it does not say how a location-scoped question is handled when the tool cannot resolve it, though 'd'autres règles dépendent du lieu' gestures at this.

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 both parameters already document their formats (AAAA-MM-JJ, empty = today; species list, empty = all). The description repeats the same four species names and adds no syntax, precedence, or formatting detail beyond the schema, so the baseline 3 applies.

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 (recreational fishing rules for Réunion, per prefect decrees) and enumerates exactly what it covers: day closures for lobster/bichiques/capucin nain/anguille marbrée, bichique hours, minimum sizes, quotas, prohibited species, lagoons. No sibling tool (maree, qualite_eau, restrictions_eau, etc.) overlaps this scope, so an agent can route to it unambiguously.

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?

The description gives concrete use cases in the form of quoted questions ('la langouste est fermée ?', 'jusqu'à quand les bichiques ?'), which tells the agent what kind of query this tool answers. It also states the caveat that other rules depend on the location and that only the decree text is authoritative, prompting the agent to defer rather than over-claim. What it lacks is an explicit pointer to any alternative or the condition for not using it.

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