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

Annotations already declare readOnly, idempotent, open-world and non-destructive, so the safety profile is covered. The description adds one valuable trait beyond them - that operations are self-describing only on demand and should be inspected via decrire_outil first - but discloses nothing about scope, result shape or limits of any operation.

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?

It is short, but the second and third sentences say essentially the same thing ('call decrire_outil with its name before use' vs 'call decrire_outil with nom = chosen operation'), wasting a third of the text on a repeat. The domain framing leads, which is good, but the message is not tightened.

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?

For a dispatcher with a large opaque enum, a free-form arguments bag and no output schema, the description does at least point the agent to the mechanism (decrire_outil) that fills the gap. It still omits any orientation about which operation suits which need, and nothing tells the agent what a successful call looks like.

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 description coverage is 0% for two required parameters, so the description must compensate and it largely does not: none of the seven operations in the enum are named or explained, and the `arguments` object (nested, additionalProperties: true) is not described at all. The only semantic offering is the instruction to look up contracts via decrire_outil, which offloads rather than explains.

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 domain (international jurisprudence, UN treaty-body committees) and hints that the tool routes among jurisdictions, treaties and legal orders, but never states plainly that it is a dispatcher over seven named operations or what a call actually returns. The verb is only implicit, so an agent must infer the tool's function from the name and the enum.

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?

It gives a usable workflow (pick an operation, then call decrire_outil with that operation name to get its contract before use), which is genuine 'when/how' guidance. It says nothing, however, about when this tool is the right choice versus siblings such as explorer_droit_europeen or explorer_jurisprudence, so sibling selection is left to the agent.

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