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

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses one important behavior: 'The owner's own permission cannot be removed.' It also implies the operation is scoped to a single permission. However, it omits details about side effects (e.g., whether other permissions are affected), reversibility, error behavior, permission requirements, and the response format. There is no annotation contradiction, but the transparency is incomplete for a destructive action.

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 two sentences with zero waste. It front-loads the action ('Take away one person's access'), then provides the crucial input source and a caveat. Every sentence earns its place; no redundant or vague wording.

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 destructive revoke operation with no annotations and no output schema, the description is fairly informative but incomplete. It explains the purpose, how to get a key input, and a major constraint, but lacks details on error handling, prerequisites (e.g., authorization), the response, and how to determine itemId. Given the tool's simplicity, it's adequate but not fully self-contained; an agent might still need to infer itemId from other tools.

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?

Schema description coverage is only 33% (mailbox has a description). The description adds value for permissionId by explaining where to obtain it (from list_gdrive_permissions) and that it cannot be the owner's. It does not describe itemId, leaving that to inference from the tool name and context. Given low coverage, the description partially compensates but does not fully clarify all parameters, especially itemId.

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 clearly states the action: 'Take away one person's access.' It's specific about the resource (Drive file) and the scope (one person's access). It implicitly differentiates from share_gdrive_item and unshare_onedrive_item through the verb and resource, although it doesn't explicitly name alternatives. The purpose is not a tautology and provides enough to understand the operation.

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 gives a direct instruction to get permissionId from list_gdrive_permissions, which is valuable context for using the tool correctly. It also warns that the owner's permission cannot be removed, a relevant constraint. However, it does not explicitly state when to use this tool versus alternatives like share_gdrive_item or unshare_onedrive_item, nor does it mention prerequisites or exclusion conditions beyond the owner constraint. The guidance is partial.

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