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

Beyond the annotations, the description discloses important behaviors: accepted authentication methods, the automatic resubmission of the application within about an hour, the revocation and replacement of the API token for rotate_token, and the limitation that rotate_token is unavailable to web sessions. These specifics add genuine transparency beyond the destructiveHint=true annotation and help the agent set correct expectations.

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 dense and front-loaded with the primary purpose, and every clause contributes substantive information. It is structured around the action values, making it fairly scannable. However, the long parenthetical-heavy single paragraph could be more readable as a concise list, so it loses one point for structural polish.

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?

Given 5 parameters, no output schema, and a destructive annotation, the description is detailed enough for an agent to select and invoke the correct action. It covers authentication, action semantics, field-specific guidance, and a key limitation. The main gap is that it does not describe the return value or response format for each action, which would be helpful since no output schema is provided.

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 input schema already covers all 5 parameters with descriptions, so the baseline is 3. The tool description adds meaningful semantics: it explains the default value of action, the meaning of view, the purpose of google_email with a concrete condition, and the functional difference of rotate_token. This enriches parameter understanding without duplicating the schema verbatim.

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 clear verb-resource pair ('View or update your account') and enumerates the specific actions available: view, update, and rotate_token. It also clarifies the scope of each action (e.g., 'view' covers account and site status; 'rotate_token' revokes and issues a new API token), which distinguishes it from related account-adjacent tools.

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 provides context-sensitive guidance: it tells agents not to ask for an sk_ token when a Bearer web session is already active, explains when to set google_email (when the on-file Google email already has an Ad Manager account or invitation), and notes that web sessions cannot use rotate_token and should use https://rocketsloth.ai/recover instead. It does not explicitly contrast this tool with all sibling tools, but the most relevant alternative (recover) is named.

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