Disconnect Google

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

Annotations only declare destructiveHint=true, and the description meaningfully adds to that: it names the two distinct effects (remote revocation of the token plus local deletion) and scopes the blast radius to 'this machine' rather than the whole Google account. It stops short of stating irreversibility or what the caller must do to reconnect afterwards.

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?

A single 11-word sentence with the destructive verbs front-loaded and zero filler. Nothing is repeated from the title or annotations, and every word carries information.

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, single-effect tool, the description is nearly sufficient: the agent knows what is destroyed and where. It could be complete by noting that access can be restored via gsc_connect, but no essential calling information is missing.

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 there is no parameter semantics to document and the baseline is 4. The description correctly implies the target is implicit (this machine) rather than user-supplied.

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 compound verb (revoke, delete) and the exact resource (this machine's Google access token), and the machine-scoping immediately distinguishes it from a blanket account disconnect. An agent can tell it apart from gsc_connect without opening either schema.

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 description says what happens but never when to call it: no prerequisite that a connection must exist first, no note that gsc_connect is the counterpart for re-establishing access, and no statement about what state the user is left in. Usage must be inferred from the tool name alone.

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