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

With no annotations, the description carries the full behavioral burden and does well: it discloses that the draft is not sent, waits in the owner's outbox, can be read/edited/sent by the owner, and returns a link. It does not cover permission or account-connection requirements, but it provides the most important behavioral traits for a draft-creation tool.

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 front-loaded, compact, and free of filler. Every sentence adds useful information, and the critical fact that the draft is not sent is placed immediately after the purpose statement.

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 tool with no output schema and no annotations, the description does a good job of explaining the non-sending workflow and the returned link. It could say more about account requirements or what to do if no mailbox is connected, but the schema covers those parameters thoroughly. The description is complete enough 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 description coverage is 100%, so the schema already documents all seven parameters in detail. The description adds only a small amount of semantic framing by tying reply_to_uid to reply creation and noting plain-text body, which does not significantly exceed what the schema provides. Baseline 3 is appropriate.

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 states a specific verb and resource ('Prepare an e-mail') and clearly distinguishes draft creation from sending by emphasizing 'It is NOT sent'. It also explains the new-vs-reply distinction. An agent can distinguish this from mail_send 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?

The description gives clear context: use it to prepare an e-mail that waits in the owner's outbox rather than being sent. It also notes reply usage via reply_to_uid and the need to give the owner the returned link. It does not explicitly name mail_send as the alternative to use when immediate sending is intended, so it falls short of full when/when-not guidance.

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