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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive. The description adds important behavioral context beyond annotations: bytes are not inlined, the download_url is short-lived with expires_at, and the output is metadata-only. This gives the agent actionable operational knowledge without contradicting annotations.

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?

Four sentences, each earning its place: primary action and returned metadata, the non-inlining caveat and expiry, the attachment_id source, and sibling tool names. No fluff 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?

Complete for a metadata-fetching tool: purpose, return values, time-sensitive URL, ID provenance, and sibling alternatives are all covered. Output schema further handles structural return details, and annotations cover safety.

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 100%, so the baseline is 3. The description adds meaningful context for attachment_id by telling the agent it comes from the attachments array of get_agentmail_inbox_message, which helps construct a valid call. Other parameters are well covered by the schema itself.

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 starts with a specific verb and resource: 'Fetches metadata for one attachment on a message' and explicitly names the thread- and draft-level twin tools, distinguishing it from related attachment tools without needing to open 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?

It gives clear context: this tool is for message-level attachment metadata, provides the source of attachment IDs ('attachments array on get_agentmail_inbox_message'), and names the sibling twins for thread and draft attachments. It also instructs to fetch the download_url before expiration, guiding correct invocation.

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