Save a draft or template

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

The description goes beyond annotations by stating 'Nothing leaves the machine, so this is not gated,' revealing that the operation is local and safe. It also explains the difference between draft (user review) and template (reusable, opened as copy). This adds valuable context not present in annotations.

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 (5 sentences), front-loaded with the primary purpose, and each sentence adds value. There is no redundancy or fluff.

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?

Given the tool's 9 parameters and two modes (draft/template), the description provides reasonable context: it explains the two use cases, the optionality of recipients, and the local nature. However, it omits details about attachments and identity_id. The presence of an output schema partially offsets the need to describe return values.

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?

With schema description coverage at 0%, the description primarily explains the 'kind' parameter (draft vs. template) and notes that recipients are optional. However, there is no explanation for other parameters (cc, bcc, body, subject, attachments, identity_id, is_html), leaving the agent without sufficient guidance for the 9 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 'Save a message without sending it, as a draft or a template.' It specifies the verb (save) and resource (message), distinguishes between draft and template, and contrasts with sending. This effectively differentiates from sibling tools like `mail_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 explains when to use this tool: 'when you want the user to review before anything is sent,' and clarifies that recipients are optional. It implies not to use for sending by mentioning 'unlike a send.' However, it does not explicitly name alternatives.

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