mail_attachment_list

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. 'List retained metadata' implies a read operation but doesn't specify what 'retained' means, whether returned selectors expire, whether message_id/account_id must reference existing records, or error behavior. The term 'retained' suggests some persistence model that is entirely unexplained.

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 a single concise sentence. It's front-loaded with the core action (List retained metadata) and mentions the selectors structure inline. No wasted words, though more substance would be welcome.

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?

This tool has no annotations, 0% parameter coverage, and a niche role in a pipeline (producing selectors). Given these gaps, the description is thin. It doesn't explain what 'retained' means, what distinguishes retained metadata from listed attachments, or the relationship to mail_attachment_stage/create siblings. An output schema exists, which slightly reduces burden for return values, but the conceptual gaps remain significant.

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%, and the description adds no parameter-level detail. account_id and message_id are self-explanatory by name, but the description doesn't clarify which message/account context the list is scoped to, or whether both are required for filtering. With zero coverage, the description should compensate and provides little beyond what the schema's names already imply.

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 'List retained metadata reusable as `{messageId, attachmentId, filename?}` selectors' states a specific verb (list) and resource (retained metadata for attachments). However, 'retained metadata' is vague—it doesn't clarify whether this lists attachments for a message or something else. The phrase 'reusable as ... selectors' hints at downstream use but doesn't clearly distinguish it from sibling tools like mail_attachment_stage or email_get_attachment.

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?

No explicit guidance on when to use this tool vs alternatives. The description mentions the output can be reused as selectors for other operations, implying a staging/pipeline role, but doesn't name any sibling alternatives or state when NOT to use this tool. 'Reusable as selectors' is the only usage hint, which is vague.

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