ask

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

With no annotations, the description bears full responsibility for disclosing behavior. It explains the tool creates a chat (side effect), sends a prompt, waits for the response, and returns it including the chat UUID for follow-ups. It also explains streaming behavior and the influence of SYNTX_STREAM_MODE, adding context beyond a simple invocation. Missing details like authentication or rate limits, but the core flow is transparent.

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 four sentences long, each contributing needed information: what the tool does, when to use it, what the response includes, and a key parameter note. It is front-loaded with the core function and avoids unnecessary detail, though slightly longer than strictly necessary.

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 tool has 8 parameters and no output schema or annotations. The description covers the overall workflow and one parameter's mode, but does not elaborate on the meanings of several parameters (e.g., `timeout`, `poll_interval`, `model_type`, `ai_name`). It also omits error handling or return structure beyond mentioning the chat UUID. This is adequate for a simple mental model but incomplete for full parameter-level understanding.

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 38%, so the description must compensate. It adds context for the `mode` parameter ('stream' opts into real-time delivery) and implies the `prompt` parameter, but leaves parameters like `timeout`, `poll_interval`, `ai_name`, `model_type`, and `scope` without any explanatory semantics. The description does not fill the gaps left by 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 clearly states the tool's function: 'One-shot helper: create a chat, send a prompt, wait for the completed assistant reply, and return it.' This distinguishes it from sibling tools like create-chat, send-message, and wait-for-response by combining these steps into a single call. The 'one-shot helper' label reinforces its unified 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?

The phrase 'Ideal for stateless Q&A' provides clear contextual guidance on when to use the tool. It also mentions the ability to opt into streaming via `mode: "stream"`, offering a specific alternative within the same tool. However, it does not explicitly mention when not to use it or compare it to the step-by-step sibling tools, slightly limiting exclusion guidance.

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