prepare_send

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

The description states 'Set save_as_draft=True to put it in Drafts instead of sending,' which is a write operation, directly contradicting the annotation readOnlyHint=true. This is an annotation contradiction, so transparency score is 1.

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?

The description is concise and front-loaded: the first sentence states the purpose. Every sentence adds value, covering non-sending, the one-time token, approval flow, from_account constraint, and draft option. No unnecessary words.

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 lays out the full workflow (preview, approval, commit_action), clarifies that nothing is sent until commit, and explains the draft option. An output schema exists, so return values are covered. However, the contradiction with readOnlyHint causes ambiguity about side effects, preventing a perfect score.

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 0%, so the description carries the burden. It adds meaning for from_account (must be from list_accounts) and save_as_draft (draft behavior), but provides no additional semantics for to, cc, bcc, subject, body, or attachments, which are standard email fields. It partially compensates but leaves gaps for many parameters.

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 clearly states that it 'Prepare a new email and return a preview for the user to approve.' It uses a specific verb and resource, and explicitly contrasts with sending by saying 'This does NOT send anything.' This distinguishes it from sibling tools like prepare_reply, prepare_forward, and commit_action.

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 provides explicit workflow guidance: show the preview to the user, and only call commit_action once they have approved it. It also specifies that from_account must name one of the accounts from list_accounts, and explains the save_as_draft option. This clearly indicates when and how to use the tool relative to siblings.

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