stream-message

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

With no annotations to rely on, the description fully carries the burden and provides substantial behavioral detail: it opens a WSS connection, streams replies, reports progress via notifications/progress when a progressToken is supplied, returns the complete text in the final result, and falls back to REST polling on transport failure unless mode is explicitly set to 'stream'. This level of disclosure exceeds typical tool descriptions.

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 well-structured sentences, immediately stating the core function and then layering important operational details. Every sentence carries meaningful information, with no redundancy or fluff.

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 output schema and no annotations, the description covers the core behavior, fallback mechanism, and progress reporting, which is commendable. However, it could be more explicit about the exact shape of the final tool result or potential error conditions, leaving moderate room for improvement.

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%, with mode, model, prompt, and timeout already described. The description adds some nuance for mode's effect on fallback, but it does not clarify the purpose of scope, ai_name, or model_type, which lack schema descriptions. Since the description doesn't compensate for these unannotated parameters, it provides only marginal value beyond the schema.

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 opens with 'One-shot streaming chat' and specifies WSS connection, prompt sending, and real-time streaming, which clearly differentiates it from sibling tools like send-message or wait-for-response. It also details the fallback to REST polling, further clarifying the tool's unique scope.

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 gives clear context for when to use the tool (streaming chat) and explains the auto/stream/poll modes, including fallback behavior. However, it does not explicitly contrast with alternative chat tools or state when not to use it, leaving some inference to the agent.

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