Draft Gmail Message

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

Annotations already convey the safety profile (readOnlyHint=false means write, destructiveHint=false means no destruction, idempotentHint=false means repeated calls create separate drafts). The description adds useful capability context beyond the annotations — supports reply drafts, optional attachments, and Send As aliases — but does not disclose behavioral traits such as where the draft lands (Drafts folder), whether signature insertion has side effects, or what happens on partial failure. The description does not contradict the annotations.

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?

Three short sentences, each earning its place: core purpose first, then scope expansion (new/reply drafts, attachments), then the Send As differentiator. No redundancy, no filler, and the most decisive information is front-loaded.

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 15-parameter tool, the schema documents every parameter fully and an output schema exists, so the description's burden is light. It adequately covers the tool's major decision points (drafting vs replying, attachments, aliases). The only gap is the absence of an explicit draft-vs-send routing statement, which is a minor omission given the tool name and sibling set make the boundary clear.

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 baseline is 3. The description references optional attachments and Send As, which map to the 'attachments' and 'from_email' params, but adds no parameter-level detail beyond what the schema already provides — and the schema's param descriptions (especially for attachments) are already very rich.

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?

"Creates a draft email in the user's Gmail account" is a specific verb+resource statement. The term "draft" cleanly separates it from the sibling send_gmail_message, and the mention of reply drafts and Send As capability adds further specificity. An agent can tell what this tool does without opening the schema.

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?

Usage context is implied rather than stated: the tool is for creating drafts, which by implication is distinct from sending (send_gmail_message) or reading (search_gmail_messages, get_gmail_message_content). However, no sibling is explicitly named, no when-not-to-use conditions are given, and no guidance is provided for choosing between 'new draft' vs 'reply draft' paths.

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