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

Beyond the readOnly/idempotent annotations, the description discloses that the tool returns metadata only, that bytes are not inlined, that the download_url is short-lived with expires_at, and that shared account use reaches inboxes created by other callers. These are meaningful behavioral details an agent needs to handle the result correctly.

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 front-loaded with the core action and scope, then adds return-field details in a compact list, and closes with routing guidance. Each sentence contributes necessary information; there is no filler.

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 simple three-parameter schema, the readOnly/idempotent annotations, and the presence of an output schema, the description is complete: it covers scope, output fields, download URL lifetime, and sibling routing. Nothing needed to call or interpret the tool is left out.

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 schema descriptions are present with 100% coverage, so the baseline is 3. The description adds value by clarifying that draft_id is sufficient 'by id alone' in the organization-wide namespace, distinguishing it from inbox-scoped identifiers. It does not deeply explain Authorization or ID formats, but the schema already covers the basic meaning.

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 opens with a specific verb and resource: 'Fetches metadata for one attachment on a draft addressed by id alone.' It clearly differentiates itself from the inbox-scoped twin by noting this is the 'organization-wide view spanning every inbox in the account.' An agent can immediately understand what this tool does and how it differs from sibling tools.

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?

Usage guidance is explicit: it describes the organization-wide scope and then names the alternative, saying 'the inbox-scoped twin get_agentmail_inbox_draft_attachment is the one to use when a single inbox is meant.' This tells the agent exactly when to choose this tool versus its sibling.

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