list-mail-attachments

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

The description adds the behavioral trait that only metadata is returned, which is beyond the readOnly/openWorld/idempotent/destructive annotations. It does not contradict the annotations, and the annotations already cover the safety profile, so this additional scoping is valuable though not exhaustive.

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?

A single, front-loaded sentence states the verb, object, and return scope with no filler. Every word earns its place.

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 list-only tool, the description plus schema and annotations cover the required messageId, optional pagination parameters, read-only behavior, and return fields (metadata only). Nothing essential is missing for an agent to call it correctly.

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 coverage is 100%, with all three parameters (messageId, cursor, maxItems) described in the input schema. The description adds no parameter-specific meaning beyond the schema, so a baseline 3 is appropriate.

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 specific action (List), resource (attachments of a message), and a crucial scoping detail (metadata only, with the exact fields returned). This distinguishes it from sibling tools like get-mail-attachment-content and list-event-attachments.

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 phrase 'metadata only: name, contentType, size' communicates the appropriate use case—listing attachment summaries without content—so an agent can infer when not to use this tool. However, it does not explicitly name the content-retrieval sibling (get-mail-attachment-content) or provide exclusion criteria, stopping short of a 5.

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