send_rich_message_draft

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

Annotations only say non-read-only, non-destructive, open-world, non-idempotent; the description adds the material facts that the draft is temporary, lives 30 seconds, and is not the durable message. It does not explain what re-sending with the same draft_id does (replace vs. accumulate), which matters for a streaming tool flagged idempotentHint=false.

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, front-loaded with the core action, then the lifetime constraint, then the escalation path. Every sentence carries information an agent needs and none is redundant.

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 nested rich_message object is documented in great depth by the schema, so the description needn't repeat formatting syntax, and it correctly covers the temporary-preview lifecycle. However, with no output schema and an unexplained required draft_id, an agent still cannot tell exactly how to establish or reuse a draft id across streaming updates.

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?

Top-level schema coverage is 25%: chat_id, draft_id and message_thread_id have no descriptions. The description mentions the draft/persist lifecycle but never explains the required draft_id (how it is chosen, whether reuse updates the preview) or what message_thread_id selects, so most of the parameter surface remains opaque.

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?

States a specific verb and resource ('Stream a partial rich message while it is still being generated') and explicitly routes the finished-content case to send_rich_message, so an agent can separate this tool from both send_rich_message and the plain send_message_draft sibling without opening any schema.

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?

Gives an explicit when (content still being generated), an explicit alternative with its condition ('call send_rich_message with the finished content to persist it'), and a hard scope exclusion ('Private chats only'). Nothing about tool selection is left to inference.

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