Create a draft

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, so the bar is lower. The description still adds useful behavior: the draft is not delivered, a shareable Gmail link is returned, and reply handling auto-fills recipients and subject — well beyond the annotation surface.

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 tight sentences: the core action and the 'NOT sent' qualifier are front-loaded, followed by supported modes and the return value. No filler.

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 12-parameter tool with no output schema, the description covers outcome (link to draft), non-delivery, and the reply/attachment capability set. It stops short of warning about the attachment path restrictions or missing-account state, but those live in the schema, leaving nothing critical unexplained.

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 83%, so the schema already documents every parameter in detail, including reply threading, send-as, and attachment restrictions. The description mostly restates those groupings (threaded replies, reply-all, signature, attachments) without adding format or constraint detail beyond them, so baseline 3 applies.

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?

States a specific verb and resource (create a draft email) plus scope (one account's Drafts folder) and explicitly rules out sending. The capability list (replies, reply-all, send-as, signature, attachments) and return value make it distinguishable from siblings like delete_draft or list_drafts.

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 'it is NOT sent' clause implies this is the compose-without-sending path, and reply modes are described. However, it never names an alternative or condition for choosing this over siblings — notably forward_email, which is the closest competing flow — so selection guidance is only implied.

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