gmail_attachments

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

With no annotations, the description carries the full behavioral burden, yet it never mentions the significant side effects implied by the schema: the tool can leave the conversation open on screen (stay_open), silently change read state and restore it (keep_unread), and abort with not_found on an expect_subject mismatch. Calling it a plain 'list' understates that it drives the UI.

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 with zero padding. It is efficient, though the terseness is part of why behavioral context is missing rather than a strength in itself.

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 six-parameter tool with no annotations, no output schema, and UI-affecting side effects, one sentence is not enough. An agent would not learn from the description that this tool may open mail on screen, toggle unread state, or fail safely on subject mismatch.

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 parameters are fully documented in structured form and a baseline of 3 applies. The description adds only the return-field list and nothing about selection precedence among index, query, and folder.

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?

States a specific verb and resource ('List the attachments of a conversation') and even names the returned fields (name, type, size, message index). It does not distinguish this from siblings like gmail_download_attachment or gmail_save_attachment_to_drive, so an agent must infer that this is the non-destructive inspection counterpart.

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?

There is no explicit when-to-use guidance and no named alternatives. Nothing tells the agent that this lists metadata only and that gmail_download_attachment or gmail_save_attachment_to_drive should be used to actually retrieve a file, nor that index/query/folder are alternative ways to select the target conversation.

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