gmail_download_attachment

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

With no annotations, the description carries the disclosure burden, and it does reveal meaningful behavior: a second copy is written to this computer, and the no-selector case fails unless there is exactly one attachment. It omits failure modes, permission/ADB prerequisites, and what the tool reports back, and the conversation-state effects (read state, stay_open) are only in the schema rather than the description.

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?

Two short paragraphs, front-loaded with the outcome (download plus copy), then the selector rules. No filler sentences, and every clause constrains how to call the tool correctly.

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 an 11-parameter, no-annotation, no-output-schema tool, the description covers the outcome and the ambiguous selector logic well. The remaining gap is the return value/result reporting and the interaction with the contextual navigation params (query/folder/index), which an agent must infer from the schema alone.

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%, so baseline is 3, but the description adds real semantics the schema does not: the three selectors are presented as an either/or choice, `name` is clarified as a case-insensitive substring match, and the fallback rule when none is supplied is spelled out. It still doesn't explain how `query`, `folder`, and `index` combine to locate the conversation.

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 specific verb and resource — download attachments of a conversation — and uniquely states the dual destination (phone Download folder plus a copy to this computer), which distinguishes it operationally from drive-oriented siblings. It doesn't name gmail_save_attachment_to_drive or gmail_attachments as the contrasting tools, so sibling differentiation is implicit rather than explicit.

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 second paragraph explains how to select an attachment (name, attachment_index, or all=true) and gives the precondition that with no selector the thread must have exactly one attachment. However, it never says when to use this tool instead of gmail_save_attachment_to_drive, nor when not to use it (e.g., no attachments, large files), which is the key routing decision for an agent here.

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