send_message_draft

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

The annotations only say readOnlyHint=false, idempotentHint=false, and destructiveHint=false, which does not tell an agent that the effect is transient. The description usefully discloses that the draft is a temporary preview requiring send_message to persist. It omits behavioral details such as whether repeated calls with the same draft_id update the same draft, and any rate limits on streaming.

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?

Two short sentences with no waste: the first states the action, and the second states the lifecycle constraint and the follow-up tool. The information is front-loaded and easy to scan.

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?

For a six-parameter streaming tool with no output schema and half its parameters undocumented, the description covers the purpose and the temporary nature but not how the draft_id lifecycle or repeated calls work. It is adequate to recognize the tool, but not fully complete for correct invocation.

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 description coverage is only 50%, and chat_id, draft_id, and message_thread_id are entirely undocumented. The description adds no meaning for any parameter, and it leaves the key parameter, draft_id, unexplained even though the tool's whole streaming/update model depends on it. With low coverage, the description should have compensated but does not.

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 a specific verb and resource: streaming a partial text message while it is generated. It clearly distinguishes itself from send_message, which persists final text. It does not distinguish itself from the sibling send_rich_message_draft, leaving a small ambiguity in the otherwise clear 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?

"Stream a partial text message while it is being generated" states when to use it, and "send the final text with send_message to persist it" names the follow-up alternative. What is missing is a when-not-to-use case, such as using send_message directly for one-shot messages, or guidance on how send_rich_message_draft differs.

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