List email attachments

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

With no annotations, the description carries the full burden. It discloses that the tool returns metadata only and does not expose bytes, which is a meaningful behavioral boundary. It does not describe return structure or error behavior, but for a simple listing operation this is reasonably transparent.

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 that communicates the core function and a key boundary in under ten words. Every part is informative and 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?

For a simple list-metadata operation, the description plus schema is sufficient. It tells the agent what the tool does, what it does not do (no bytes), and the schema documents the parameters. Minor omissions like output format are acceptable here.

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 both 'id' and 'account' are already documented in the schema. The description adds no additional parameter-level meaning, meeting the baseline for a fully covered 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 states a specific action and resource: 'List attachments on a message', and immediately clarifies the scope with 'metadata only, no bytes'. This clearly differentiates the tool from google_gmail_get_attachment, which retrieves actual attachment bytes.

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, no bytes' effectively tells the agent when to use this tool: when only attachment metadata is needed, not content. It implies the alternative but does not explicitly name google_gmail_get_attachment or state concrete conditions, leaving slight room for inference.

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