Disconnect Account

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

Annotations declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, and the description adds exactly the value annotations cannot: what specifically is destroyed (cached device-auth credentials) and what survives (environment API key). It also discloses that a confirmation is returned, so the agent knows the effect is verifiable.

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 sentences: the first front-loads the invocation condition, the second discloses the effect and its boundary. Every clause carries information and nothing is repeated from the title or annotations.

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 zero-parameter, no-output-schema tool with rich annotations, this covers trigger, effect and side-effect boundary. The only small gap is that it does not say whether the caller must re-run auth_login afterwards or whether other tools will start failing after logout.

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 is 4; there is nothing for the description to disambiguate. It correctly avoids inventing parameter detail for a no-arg call.

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 action (clearing cached device-auth credentials) tied to concrete user phrasings ('log out', 'sign out', 'disconnect', 'switch accounts'), which clearly separates it from the sibling auth_login and auth_status tools. It does not explicitly name those siblings, but the intent is unmistakable.

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 explicit trigger conditions via quoted user utterances, and it also states a when-not nuance: an API key set in the environment is not revoked, so the agent knows this tool does not fully de-authenticate env-key users. No inference is required to decide when to call it.

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