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

Annotations only say readOnlyHint=false and destructiveHint=false, which merely flags a non-destructive write. The description adds two things annotations cannot convey: the secret is returned exactly once ('secret retourné une seule fois'), so the agent knows to surface it immediately and never expect to retrieve it again, and an owner-level key is required. What it omits is whether key creation is rate-limited, logged, or capped per project.

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 clauses, both load-bearing, with the one-time-secret warning not buried. The only inefficiency is the language switch relative to the English tool ecosystem, which slightly raises parsing cost but costs no words.

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 two-parameter creation tool with no output schema and no parameter descriptions, the description covers the single most important behavioral fact (one-time secret) and the auth requirement. It leaves the agent guessing about the role parameter's meaning and default, which is a meaningful gap for a security-sensitive tool granting admin by default.

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%, so the description must carry the parameter burden, and it does not. Neither 'name' nor 'role' is mentioned; in particular the role parameter with its viewer/editor/admin/owner enum and default of 'admin' is a privileged choice left entirely unexplained.

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 states a specific verb and resource ('Créer une clé pour ce projet'), so the agent knows this mints an API key scoped to the current project. It does not name its obvious siblings (list_api_keys, revoke_api_key), and it is written in French while the rest of the tool surface is English, but the purpose itself is 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?

The prerequisite 'Clé propriétaire requise' tells the agent an owner-level credential must be in place before calling, which is genuine usage guidance. However, there is no statement of when to prefer this over list_api_keys or revoke_api_key, and no guidance on naming or role selection when creating a key.

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