audit_external_permissions

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

No annotations are provided, so the description must carry the burden. It explains the tool flags external permissions and provides the GAM command, but does not explicitly state whether it is read-only, what side effects exist, or authorization needs. The GAM command implies a read operation, but not stated directly.

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 structured with a title, purpose statement, parameter list, and GAM command. It is concise and front-loaded with the purpose. The GAM command adds length but provides useful implementation detail.

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 the presence of an output schema, the description does not need to explain return values. It covers purpose, parameters, and usage context. It lacks explicit output or error information, but the GAM command and context provide sufficient completeness for a tool with this complexity.

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 coverage is 0%, so the description lists parameters with brief explanations (e.g., 'The email of the user who owns the source folder.'). These add some meaning beyond parameter names but are minimal; for example, 'domain' includes an example value. Overall, the parameter descriptions are helpful but not rich.

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 starts with 'Step 7 — Files shared with users outside your organisation.' and states it 'flags files that have at least one permission entry for a user NOT in the specified domain.' This provides a specific verb and resource, clearly differentiating from sibling audit tools like audit_all_permissions or audit_public_files.

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 mentions that flagged files 'may require cleanup or re-evaluation before migrating to a Shared Drive,' providing context on when to use the tool. However, it does not explicitly state when not to use it or name alternatives, though the sibling list implies other tools for other audits.

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