gmail_create_draft

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

The description says 'never send' and indicates a non-destructive draft creation, but the annotations declare destructiveHint=true. This is a serious contradiction about the operation's side effects, so transparency is undermined.

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 short sentences are front-loaded with the core purpose and give compact, relevant guidance without unnecessary detail.

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?

The description provides key retry semantics but misses important schema context such as the required text field, recipient structure details, and replyToMessageId. Given zero schema descriptions, this leaves significant gaps and includes a misleading statement about required recipients.

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?

The schema has no property descriptions, and the description only explains requestId idempotency and mentions accountId and structured recipients. It omits required text and replyToMessageId semantics, and wording like 'structured recipients ... are required' conflicts with the schema, where to/cc/bcc are optional and text is required.

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 the operation with a specific verb and resource: 'Create a draft, never send.' This distinguishes it from the read/search/calendar siblings and clarifies the intended side effect.

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?

It provides useful usage context, especially idempotency guidance: 'Reuse the same requestId for retries; ambiguous creates are not retried.' It also emphasizes that the operation does not send, but it does not explicitly compare against alternative sibling tools.

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