send_message

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

No annotations are provided, so the description must do the work of explaining behavior. It is transparent about the asynchronous nature of sending: success indicates only that the message is queued, not delivered, and the message may be found in Sent or Outbox. This adds real behavioral context beyond the basic 'send an email' understanding.

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 compact and front-loaded with the core action, then adds the two most important non-obvious behaviors: queued success and delivery verification. Every sentence contributes meaningful information with no fluff or redundancy.

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 covers the most critical contextual need: understanding the difference between a queued send and actual delivery, and knowing where to verify the outcome. Combined with a fully documented input schema, this is sufficient for an agent to call the tool correctly. It could be even more complete by explicitly naming another send-related sibling, but that is a minor gap.

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 description coverage is 100%, so the parameters are already well documented individually. The description itself adds little param-specific meaning beyond indicating the message body is plain text, which is minor. Thus the baseline of 3 applies.

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 opens with a specific verb and resource: 'Compose and send a new email message as plain text.' This clearly identifies the tool's main action and differentiates it from sibling tools like reply_to_message, forward_message, move_message, etc. It also adds the unique nuance that sending is only queueing, which further defines the purpose.

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 tool is clearly for new outbound email messages, and the description provides a useful follow-up instruction to check Sent/Outbox for delivery verification. However, it does not explicitly address when to avoid this tool and choose a sibling such as reply_to_message or forward_message, so the alternative-routing guidance is only implied.

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