Remove a permission from a Google Drive file by permission ID or email address, or revoke link sharing by using 'anyone'. Use it to stop specific people or public access.
WRITES. Remove one permission, by permission id (from get_file_permissions) or by the email address it was granted to. Pass emailAddress "anyone" to remove link sharing.
| Name | Required | Description | Default |
|---|---|---|---|
| fileId | Yes | ||
| emailAddress | No | ||
| permissionId | No |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the behavioral burden; the 'WRITES' marker and 'Remove one permission' disclose the mutation and its narrow scope. However, it omits reversibility, error/idempotency behavior, and whether both identifiers can be supplied together, leaving notable gaps for a destructive-style write.
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?
Extremely compact, with the operation class front-loaded ('WRITES.') and the identifier options following immediately. Every clause carries information; nothing is padded.
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 single-purpose mutation tool with no annotations and no output schema, the description covers the essential inputs and the link-sharing special case. It stops short of describing failure modes or whether the operation is idempotent, but it is sufficient to invoke correctly.
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 0%, so the description must compensate, and it does for two of three params: permissionId's provenance (get_file_permissions) and the emailAddress special value 'anyone' for link sharing. Only fileId is left implicit, but that is self-evident.
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 verb and resource ('Remove one permission'), scoped to a single permission, which clearly distinguishes it from the sibling share_file and from get_file_permissions. The 'WRITES' prefix immediately signals the operation class.
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?
Gives clear context: identify the permission either by id obtained from get_file_permissions or by the granting email, and names the 'anyone' value for link sharing. It does not explicitly contrast with share_file or state when-not-to-use, but the conditions for each input path are spelled out.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.