Send an existing draft (two-phase)

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

Annotations declare destructiveHint=true, readOnly=false, and idempotent=false. The description adds the key behavioral trait of two-phase operation (preview before send), which is not captured in annotations. It clarifies that calling without the token is only a preview, not a send. No contradiction.

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 sentences, front-loaded with the core purpose. Every phrase contributes: 'existing draft' implies use case, 'preview' and 'send' outline the two-phase flow. No redundant wording.

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?

The description fully explains the two-phase workflow, which is the most critical context. With no output schema, it does not specify the return format, but 'preview it' suggests that the first call returns a preview. Given the simple parameter set and annotation support, it is sufficiently complete for an agent to invoke correctly.

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 has zero parameter descriptions, so the description must compensate. It explains confirm_token's role explicitly ('Call without confirm_token to preview it, then again with the token to send'). However, account and draft_id are left to inference from their names; no additional meaning is provided for them.

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 'Send a draft that already exists', which clearly names the verb (send) and resource (draft). The title adds 'two-phase', distinguishing it from a direct send tool. It is distinct from siblings like gmail_create_draft and gmail_send.

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 description gives explicit usage steps: 'Call without confirm_token to preview it, then again with the token to send.' This tells the agent exactly how to perform the two-phase flow. It does not name alternative tools, but the context of 'existing draft' implies when to use it.

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