Sources des données

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

Annotations already declare readOnlyHint=true, openWorldHint=true and idempotentHint=true, so safety is covered. The description adds genuinely non-structured context: that the payload includes licence and attribution obligations ('attribution à citer') and that some data may not yet be covered. Those are behavioral facts an agent cannot derive from the annotations.

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 French sentence front-loads the content inventory and the usage rule well, but the English half is a compressed restatement that mostly repeats it rather than adding information. It is bilingual by design, which is defensible for a French-language server, though the duplication does not earn full marks on efficiency.

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 carries the burden of saying what comes back, and it does: sources with licence/attribution, coverage gaps, tool list, latest changes. The internal structure of the response is not spelled out, but that is a minor gap for a self-documenting catalogue tool.

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?

There are zero parameters and 100% schema coverage, so the baseline is 4. The description adds nothing parameter-related because there is nothing to add.

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 the specific resource it exposes: data sources used by the server (organism, licence, attribution), coverage status, the current tool list, and recent changes. This clearly distinguishes it from every data-bearing sibling in the list, none of which is a catalogue/meta tool. It lacks an explicit verb but the enumeration of contents makes the purpose unambiguous.

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?

"À appeler avant de conclure qu'un outil ou une donnée n'existe pas" gives a concrete trigger condition, which is exactly the guardrail an agent needs before making negative claims about coverage. It does not state a when-not condition, but for a zero-cost read-only meta tool there is little reason not to call it.

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