qwen_reply

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

With no annotations provided, the description carries the full burden and delivers richly: it discloses that sessions survive timeouts/cancels in qwen's own store, survive server restarts, and that qwen never sees this conversation (so the follow-up should be short). The parameter texts add further behavioral detail (effort only applies to stream transport and is rejected in print mode; timeout-killed runs still return their session id and are resumable), going well beyond what the schema names alone imply.

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?

Four sentences, zero filler, and the core purpose plus scope constraint are front-loaded in the first clause. Every sentence earns its place: purpose/scope, persistence rationale, context-separation note, and sibling routing. Dense but efficient.

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 10-parameter, 3-enum tool with no output schema, this is nearly complete. It explains the session lifecycle, resumability guarantees, how to obtain a session id, and routes to the correct sibling for a running turn. All parameters are documented, and the nuance about context separation helps the agent craft an appropriately scoped follow-up.

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% and the property descriptions are already behavior-rich, so the baseline is 3. The main description adds genuine value on top for the two required params: session ('the session survives… resume it here') and prompt ('the follow-up can be short'). That lifts it above baseline, though individual property semantics are largely carried by the schema itself.

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 ('send a new turn to an existing qwen session') plus a hard scope constraint ('not executing right now', including timed-out or cancelled sessions). It explicitly names sibling alternatives (qwen, qwen_send) and the conditions that select between them, so an agent can distinguish it without opening a 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?

Gives explicit when-to-use ('resume it here instead of restarting with qwen'), when-not-to-use ('For a turn still running under stream, use qwen_send instead'), and names the alternatives directly. Also communicates the follow-up can be short because qwen retains prior turns — practical guidance for how to phrase the prompt.

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