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

Beyond the annotations, it discloses concrete effects: binding deletion, key revocation, fallback to keyless trial, own API key untouched, and safe when nothing is linked. This is rich behavioral context beyond the readOnly/destructive/idempotent hints.

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?

The description is front-loaded with the core action, follows with consequences, and then gives usage scenarios. Every sentence adds decision-relevant information, including safety and cost, without padding.

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, the description fully covers when to call it, what happens, what does not happen, and post-call behavior. Nothing needed to invoke it correctly 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 and schema description coverage is 100%, so there is no parameter burden for the description to carry. Baseline 4 applies; no additional parameter detail is needed.

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 opens with 'Undo `link_account`' and specifies the resource and effect: the binding is deleted and the client key revoked. This clearly differentiates it from its sibling link_account and from account-level operations like create_account or account closure.

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 conditions for use: on any machine that is not yours, or whenever a personal connector URL or client id may have been exposed. It also states what it is not for ('does not close an account') and frames link_account as the inverse operation.

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