send-draft-message

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

Annotations already indicate destructiveHint=true, so the description adds context by stating it saves in Sent Items. However, it does not disclose what happens to the original draft after sending (presumably deleted) or any permission requirements. The description adds some value but is not rich.

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 relatively short but includes an unclear alternative statement that could be omitted or clarified. The tip is useful. Overall, it could be more concise without losing key information.

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, the description should explain return value or result. It only mentions saving in Sent Items but not what is returned. The alternative operation is vague. Given the complexity of drafts and sibling tools, the description feels incomplete.

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 100%, so the description does not need to add much param info. The tip reinforces that no body is needed, but this is already evident from schema. No extra semantics are provided beyond the schema.

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 'Send an existing draft message' which is clear verb+resource. However, it adds confusion by saying 'Alternatively, send a new message in a single operation' without clarifying if that is a separate capability overlapping with sibling tool send-mail. This ambiguity detracts from clarity.

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 mentions a prerequisite ('Draft must exist in Drafts folder') and a tip ('No request body needed'), but it does not provide guidance on when to use this tool versus alternatives like send-mail, nor does it exclude cases where this tool should not be used.

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