stream-message

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

With no annotations, the description carries the full burden and does well: it discloses the SSE connection, REST polling fallback on transport failure, progress notifications, and that the final result contains the complete text. It omits auth, rate-limit, error-surfacing, and retry details.

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 sentences, front-loaded with the main purpose, and each clause adds useful transport, progress, or result information. There is no filler.

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 streaming tool with no annotations or output schema, the description covers transport, fallback, progress reporting, and final output adequately. It still lacks parameter-choice guidance and error-condition detail, so it is not fully complete.

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 coverage is 57%, and the description adds meaning for streaming mode, fallback behavior, and progressToken handling. It leaves model, ai_name, timeout, model_type, and the scope default largely unexplained, so it only partly compensates for the coverage gap.

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/resource ('streams the assistant reply') and scope ('text scope'), plus the transport mechanism. It does not explicitly name the sibling to use instead, such as send-message or ask, so differentiation is implied rather than spelled out.

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 phrase 'one-shot streaming chat' and the fallback behavior imply when this tool is useful, but the description never states when to choose it over send-message, ask, or wait-for-response, nor when not to use it.

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