send-draft-message

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

Discloses that the message ends up in Sent Items and that the draft must exist in the Drafts folder. This adds context beyond the annotations (destructiveHint=true, openWorldHint=true), which already indicate mutation and potential side effects. No contradiction with 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?

Three short sentences plus a tipped line, all front-loaded with the core action. No extraneous content. Every sentence serves a purpose.

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?

Covers the main action, prerequisites (draft in Drafts folder), and a key behavioral aspect (saved to Sent Items). Lacks details on return values or response format, but for a straightforward send operation with no output schema, the description is largely sufficient.

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?

Input schema has 100% description coverage, so the description adds limited new parameter information. The tip about 'no request body needed' is helpful but does not elevate the score above baseline for parameter semantics.

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?

Describes a specific action: 'Send an existing draft message.' Distinguishes between draft types (new, reply, reply-all, forward) and mentions an alternative usage for sending a new message in one operation, clearly differentiating from sibling tools like create-draft-email or send-mail.

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?

States when to use (sending an existing draft) and hints at an alternative (sending a new message in a single operation), but does not explicitly name which sibling tool covers that alternative or specify when not to use this tool. The tip about no request body and draft location provides practical guidance.

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