mail_draft_email

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

With no annotations, the description bears full burden. It discloses that the tool never sends, appends a signature when sender is set, and strips em dashes. These are important behavioral traits beyond a basic draft creation. However, it doesn't mention whether it creates a new draft or modifies an existing one, nor error conditions.

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 sentences, front-loaded with the most important point (never sends). No unnecessary words, directly addresses key behaviors.

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 an 8-parameter tool with low schema coverage and no output schema, the description provides essential context (no sending, signature behavior, em dash stripping). It could mention whether the draft is created or opened, and return value, but given sibling tools like mail_draft_reply, it is fairly complete.

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 low (38%). The description adds critical context: 'never sends' clarifies the tool's action, 'appends signature from signatures/ when sender is set' relates to the 'signature' and 'sender' parameters, and 'em dashes stripped' adds meaning to 'subject' and 'body'. Other parameters like to, cc, bcc, attachments are not elaborated, but the description partially compensates.

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 it opens a draft and never sends, which is specific to composing emails. It distinguishes from sibling 'mail_draft_reply' which likely creates a reply draft.

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 explicitly says 'never sends,' which tells the agent this tool only opens a draft and does not send. It implies use for composing drafts without sending, but does not explicitly state when to use over alternatives like mail_draft_reply.

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