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

Annotations already cover readOnly/non-destructive/closed-world, so the bar is lower; the description still contributes two non-obvious facts: secret values are stripped from results, and an owner key is mandatory. That is meaningful context beyond structured fields, though nothing is said about pagination or ordering.

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?

Two short sentences, front-loaded with the action and then the constraint, with no filler. It is slightly under-specified rather than verbose, and the French phrasing in an otherwise English tool family is a minor readability cost.

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 no-parameter read-only list operation, the description covers the essential facts: what is returned (keys minus secrets) and the authorization requirement. No output schema exists, so a brief note on result shape would have been the only remaining gap.

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 zero parameters, which sets the baseline at 4. Nothing in the description is needed to disambiguate arguments, and it adds none.

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?

States a specific verb+resource ('Lister les clés') and adds a scoping detail (sans leurs secrets) that separates it from create_api_key and revoke_api_key. It does not name those siblings explicitly, 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?

There is an implicit prerequisite ('Clé propriétaire requise') telling the agent it needs an owner-level key, which is real routing value. However, there is no explicit statement of when to prefer this over describe_resources or other listing tools, nor any exclusion.

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