send_message_draft

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

The description discloses a key behavioral trait—content appears progressively—which adds value beyond the annotations. However, it does not explain what 'draft' means (e.g., whether the message is temporary or will be replaced), nor other implications like editing or cancellation. Given the annotations only hint at read/write safety, this level of transparency is moderate.

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 two succinct sentences with the core action front-loaded in the first sentence. It contains no extraneous words or repetitive content, making it an excellent example of conciseness.

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?

Given the tool's 12 parameters and lack of an output schema, this brief description is insufficiently complete. It omits return value information, usage prerequisites, and any alternative tool mentions, leaving the agent with only the streaming behavior as extra context.

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 description provides no additional meaning for the parameters beyond the schema. With schema description coverage at 50%, the description does not compensate for undocumented parameters such as entities or effect_id, leaving semantic gaps that could confuse the agent.

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 uses the specific verb 'Send' with the resource 'draft message' and the qualifier 'streaming', clearly distinguishing it from the sibling send_message. The added phrase 'Content appears progressively as it's being generated' reinforces its unique behavior, leaving no ambiguity about its primary function.

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 implies usage when streaming or progressive content is desired, but it does not explicitly state when to use this tool versus alternatives like send_message. No exclusions or alternative tool names are provided, so the agent must infer the context from the 'streaming' qualifier.

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