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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the bar is lower. The description still adds real behavioral context beyond them: authentication completes in the person's browser, meaning this tool never performs the auth handshake and the agent must not expect to drive login through it. That out-of-band completion note is exactly the kind of context worth stating.

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?

Three short sentences, front-loaded with the state check followed by the login URL and the browser-completion caveat. Nothing is padded. Minor friction: the description is in French while the tool name and title are English, which can slow an agent scanning mixed-language definitions.

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 should convey what a caller receives (e.g. a boolean authenticated flag, an identity-provider name, a session expiry). It explains what the tool does not do (no login flow) but stops short of describing the returned state, leaving the response shape entirely unstated.

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, so the baseline of 4 applies; there is nothing for the description to disambiguate. No parameter discussion is needed or expected.

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 says it reports "État de la connexion Google/Keycloak" – the state of the Google/Keycloak connection – which is a recognizable resource, but the verb is implicit and the scope is ambiguous. It is not clear whether this is a per-user session check or a global identity-provider status, and it is not distinguished from near-siblings such as get_identity, list_connections or describe_connections that also concern connections.

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 second sentence gives a concrete routing directive: to actually log in, open the /api/auth/google URL rather than calling a tool. That implies this tool is for checking state, not performing login. However, no explicit statement of when to call it versus get_identity or configure_connection is given, so usage is only implied.

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