ofw_send_message

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

The description goes beyond the destructiveHint annotation by detailing when deletion occurs (draft), how replyToId gets rewritten, and the post-send caching behavior. These are valuable behavioral insights that help the agent understand side effects.

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 yet thorough. It starts with the core purpose, then uses conditional language to explain distinct workflows, and adds necessary caveats about reply-to rewriting and post-send caching. No sentence is extraneous.

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 workflow, side effects, and parameter interactions well. However, it does not describe the return value (beyond caching) or potential errors. For a tool with no output schema, the agent would benefit from knowing what the response contains (e.g., the sent message object).

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?

While the input schema already describes each parameter, the description adds crucial behavioral context: the overriding mechanism when messageId is used, the legacy relationship between draftId and messageId, the rewriting behavior of replyToId, and the source of fileIds. This goes beyond the schema's static descriptions.

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 'Send a message' and explains two distinct workflows: sending an existing draft (which deletes the draft) or sending a fresh message. This distinguishes it from sibling tools like ofw_save_draft (saves without sending) and ofw_delete_draft (deletes without sending).

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 clearly outlines when to use each mode (draft vs fresh). However, it does not explicitly state when NOT to use this tool (e.g., for saving drafts) or direct the agent to sibling tools like ofw_save_draft for alternative operations. This implicit guidance is good but lacks explicit exclusion.

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