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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds only the qualifier 'vérifiée' (verified data), which hints at curation but does not explain scope, granularity, or whether it covers all territories or only curated ones. With no output schema, no return-shape context is given at all.

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?

One front-loaded sentence, no filler or repetition. It is arguably too terse given the absence of an output schema, but nothing in it is wasted.

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 parameters and no output schema, the description is the only place an agent can learn what this aggregate returns — and it does not say. It also leaves unclear how it relates to observatory_caribbean_brief, a near-name twin, which is the main risk for mis-selection.

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?

The tool takes no parameters and the schema is trivially complete, so there is nothing for the description to compensate for. Baseline 4 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 single sentence names a resource ('couverture culturelle vérifiée de la Caraïbe') and a shape ('vue agrégée'), so the agent knows this is a read-only aggregated view for a region. However it does not say what is inside the aggregate, and it fails to distinguish itself from the sibling 'observatory_caribbean_brief', which sounds like an alternative rendering of the same Caribbean data.

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?

There is no statement of when to use this versus the Caribbean brief or the global/regional observatory siblings, and no prerequisites or exclusions. The agent must infer selection purely from the name.

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