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

Annotations already declare read-only, idempotent, and non-destructive behavior, and the description extends this with the guarantee that it never executes attachment content. The phrase 'bounded text preview' and 'authenticated file reference' add useful behavioral detail about preview limits and access modes that annotations alone do not convey.

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 two short sentences with no filler; the primary capability appears first and the safety caveat is front-loaded in the opening sentence. Each clause contributes distinct information: access modes, the preview bound, the file-reference form, and the non-execution guarantee.

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 rich input schema, presence of an output schema, and annotations covering read-only/idempotent behavior, the description supplies the missing contextual framing: what the tool returns in each mode and that it never executes content. The oneOf source ambiguity and mode constraints are already fully documented in the schema.

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 schema already defines source, mode, cursor, and maxChars in detail. The description's mention of a bounded preview maps to maxChars and preview mode, but it does not add parameter syntax or additional semantic meaning beyond the schema.

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 precise verb-resource pairing ('Get attachment metadata...') and enumerates the three output forms: metadata, bounded text preview, or authenticated file reference. It also asserts a safety boundary, 'Never executes attachment content,' which distinguishes the tool from anything that processes or runs attachment payloads.

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 description makes the tool's purpose clear enough that an agent can infer when to call it for attachment access, but it does not explicitly state when to prefer this tool over siblings such as get_message or import_attachment. The only exclusionary language is 'Never executes attachment content,' which is a safety boundary rather than a routing rule.

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