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

With no annotations, the description carries the burden. It discloses a non-obvious behavioral trait: results include grants made outside Higgs Hub. It also highlights the permissionId as a key output needed for revocation. However, it does not explicitly state that the operation is read-only or describe any auth requirements or rate limits. The verb 'List' implies read-only, and the added scope and output details exceed the minimum, so 4 is warranted.

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 a single, front-loaded sentence: the core action ('List everyone with access to a file') comes first, followed by two valuable qualifiers. There is no filler, every clause earns its place, and it is easy to scan.

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 simple two-parameter list tool, the description covers the main purpose and the key output field, but it omits any explanation of itemId, the return structure, or pagination/error behavior. There is no output schema to fill in the gap, so an agent might know what the tool does but not exactly what it needs to pass or what it gets back. Adequate but with clear gaps.

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 description does not clarify either parameter. The input schema describes mailbox but leaves itemId completely undefined, and the description does not compensate for this 50% coverage gap. The agent is left to infer that itemId is the Drive file ID, which is a significant omission for a tool whose only two parameters need both to be correct.

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 uses a specific verb and resource: 'List everyone with access to a file.' It adds distinguishing details—'including grants made outside Higgs Hub' and 'permissionId needed to revoke one'—that set it apart from siblings like list_gdrive_items or list_onedrive_permissions. An agent can clearly tell this lists permissions for a Drive file, not files or calendars.

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 implies when to use this tool: when you need the list of all access grants on a Drive file and specifically the permissionId to revoke one. It gives clear context, though it does not explicitly name alternatives or state when not to use it. The schema's mailbox parameter also points to list_authorized_mailboxes, but that is outside the description. Overall, the usage context is clear with no exclusions or misleading cues.

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