mail_create_draft

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

Describes the operation as creating an unsent draft and explicitly states no send capability, but the annotations include destructiveHint=true, which contradicts the non-destructive nature of creating a draft. This mixed signal reduces transparency.

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 information-dense, with no filler. Each sentence adds meaningful constraints or capabilities.

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?

With no output schema and complex nested parameters, the description covers key constraints but omits expected return behavior, idempotency implications of requestId, and any error conditions, leaving gaps for an agent to infer.

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?

Description adds context about validated To/Cc/Bcc, Unicode JSON bodies, and HTML formatting restrictions, but does not explain the purpose of requestId, the body object's format/content fields, or the nested recipient structure beyond what the schema already shows.

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?

Clearly states the tool creates an unsent draft, requires accountId and requestId, and explicitly notes that it does not send emails. This distinguishes it from sending and reply-draft tools.

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?

Provides explicit requirements (accountId, requestId) and limitations (no send, HTML attribute-free), but does not directly contrast with sibling tools like mail_create_reply_draft or when to prefer this tool.

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