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

With no annotations, the description carries the burden of behavioral disclosure. It reveals non-obvious traits: the person is NOT emailed, Google-account requirement, and the confirmation step. It could additionally mention reversibility or side effects on existing permissions, but the key behavioral surprises are disclosed.

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 sentences with no filler: action and return value, key constraint, notification guidance, and a safety instruction. Each sentence earns its place and the most important information is front-loaded.

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 sharing tool with no annotations or output schema, the description covers the core workflow well: who gets access, what is returned, what does NOT happen automatically, and the need for user confirmation. It could be improved by suggesting how to find itemId or mentioning that access can later be removed, but it is not incomplete enough to mislead.

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 most parameters. The description adds little beyond the schema, though it clarifies itemId refers to a 'file or folder.' It doesn't explain how to discover itemId (e.g., via list_gdrive_items), which would be useful but isn't necessary given the high coverage.

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: 'Give a named person access to a file or folder by their email address' and explicitly mentions returning the link. It is specific enough to distinguish from siblings like share_onedrive_item or unshare_gdrive_item, and the title reinforces the resource.

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?

Provides clear context: only named people, no 'anyone with the link' option, and explicit instruction to use send_gmail_message for notification instead of expecting an email. It also tells the agent to ask the user for confirmation before sharing. It doesn't explicitly name alternatives like list_gdrive_permissions, but the main routing guidance is present.

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