list_attachments

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

With no annotations, the description carries the full burden. It usefully discloses that the tool returns metadata only and never content, but it does not explain the behavior controlled by include_raw or any side effects. This is partial disclosure, not full transparency.

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?

One sentence with a parenthetical that earns its place, front-loading the key distinction (metadata only, no content). No filler or redundancy.

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 low-complexity list tool, the description covers the core scope, but it leaves gaps: include_raw is ambiguous, mailbox is unexplained, and there is no output schema or annotation context. Adequate yet incomplete.

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 0%, so the description needed to compensate, but it explains none of the three parameters explicitly. Only 'on a message' hints at message_id; mailbox and include_raw receive no semantic clarification.

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 attachments on a message,' and sharpened by 'metadata only — no content.' This clearly distinguishes it from content-returning siblings like download_attachment and download_hosted_content without needing to open their schemas.

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 'metadata only — no content' caveat gives clear context for when to choose this tool over alternatives, implying that content retrieval should go elsewhere. It does not explicitly name the alternative tool, but the guidance is not misleading.

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