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

Annotations only declare readOnly=false, openWorld=true, destructive=false. The description adds real behavioral context beyond that: the recipient is NOT emailed, link-only sharing is unsupported, and user confirmation is required first. It doesn't cover revocation semantics or how existing permissions interact, but the safety-relevant caveats are well surfaced.

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?

Three front-loaded sentences with no waste: the core action first, then the constraint, then the non-email caveat and confirmation instruction. Emphasis (bold) is used sparingly on the most easily-missed fact.

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?

No output schema exists, and the description adequately notes that a link is returned. For a permission-granting mutation tool, the main agent-relevant caveats (no public links, no auto-email, confirm first) are all present; minor gaps remain around expiration and role choice.

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 80%, so the schema already documents mailbox, email, role (enum with default), and expiresInDays. The description adds only that access is granted by email address; it says nothing about role choices or the expiry parameter, so the baseline 3 applies.

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 (give access), resource (file or folder), and mechanism (by email address), plus the return value (the link). It is clearly distinguishable from siblings like unshare_gdrive_item, list_gdrive_permissions, and share_onedrive_item.

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?

Explicitly constrains usage: only named people, no 'anyone with the link' option, recipients without a Google account cannot be granted access. It routes the agent to send_gmail_message for notification and instructs confirming with the user before sharing — clear when/when-not guidance and a named alternative.

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