send_draft

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

With no annotations at all, the description carries the full burden and it does disclose the most important behavioral trait: a preview + confirm_token handshake before the irreversible send. It does not state irreversibility explicitly, mention permission needs, or describe what the preview contains or how tokens expire, which prevents a 5.

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, front-loaded with the action and immediately followed by the non-obvious workflow. Nothing is redundant, though the `account` note reads as an afterthought appended after the workflow rather than integrated.

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 destructive, unannotated, no-output-schema tool, the description covers the critical two-step mechanic but omits what happens on a bad or expired token, whether the send is reversible, and what the preview returns. These gaps matter given the absence of annotations and output schema.

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 0%, so the description must compensate, and it explains both `account` (an email or alias) and `confirm_token` (obtained from the first call and required on the second). `draft_id` is left entirely undocumented, and no format or sourcing guidance is given for it.

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?

"Send an existing draft" gives a specific verb and resource, and the word "existing" distinguishes it from create_draft/create_reply_draft and from send_email, which would compose-and-send in one step. It stops short of naming those siblings explicitly, so the differentiation is implicit rather than stated.

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 two-step invocation is clearly spelled out, which is the main usage guidance an agent needs. However, there is no statement of when to prefer this over send_email, nor any prerequisites such as the draft needing to exist in the given account.

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