qwen

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

With zero annotations, the description carries the full burden and delivers thoroughly: it discloses blocking-until-settle behavior, the output shape (final result plus stats, prefixed [session: <id>]), the separate-context limitation (qwen cannot see this conversation), the yolo approval default that edits files and runs shell commands as the user without asking, kill-time resumability, and stream-vs-print reachability semantics. This is exemplary behavioral disclosure for a mutation-capable tool.

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?

Well-organized in descending importance: core purpose first, then return format and session routing, then 'Good for' usage, then the safety caution. Although on the longer side, every sentence conveys distinct information — parameter implications, failure resumability, and approval semantics all earn their place with 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 complex 9-parameter tool with no annotations and no output schema, the description covers the full operational picture: blocking behavior, output contract with session-id prefix, the self-contained-prompt requirement, safety default, failure mode (resumable on kill), and integration with siblings (qwen_reply, qwen_send). Nothing an agent needs to invoke it correctly is missing.

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 100%, so the baseline is 3. The description adds genuine value beyond the schema by contextualizing approval_mode (yolo defaults to full delegation, 'delegation is the point'), allowed_tools (pairs with yolo for read-only runs), transport (steerability via qwen_send), and cwd (where qwen edits and reads QWEN.md). This meaningfully exceeds the baseline by linking parameters to behavioral consequences.

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 ('Start a NEW task in the local Qwen Code agent') and explicitly frames it as a separate agent with its own file/shell tools and context window. The 'NEW task' emphasis and 'continue that session later with qwen_reply' directly distinguish it from all siblings (qwen_reply, qwen_send, qwen_models, qwen_running, qwen_sessions) 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?

Provides explicit 'Good for' scenarios: a second opinion from a different model, work kept out of this context, and parallel investigation. It implies routing (continue with qwen_reply) and steers safety-constrained usage via the caution. However, it lacks an explicit 'when not to use' or a comparative list against the sibling tools, leaving some selection logic to inference.

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