route

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

With no annotations, the description carries the full disclosure burden, and it does add a real behavioral fact: the response carries an abstained flag and the correct fallback is refusal, not a best guess. However, an agent still learns nothing about the rest of the return payload, the label set of predefined flows, or the handling of non-Chinese queries.

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?

One sentence split by a semicolon: the routing action first, the abstention rule second. Every clause carries new information and nothing is redundant.

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 router with a single string input this is close to adequate, since the abstention contract is the critical behavior. But with no output schema and no enumeration of the candidate flows, the agent cannot tell what a successful response looks like beyond the abstained flag, leaving a meaningful gap.

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?

There is a single required parameter with 100% schema coverage, so the baseline is 3. The description contributes one constraint beyond the schema, namely that the query should be Chinese-language user speech, but adds no detail on length, quoting, or whether the raw utterance can be paraphrased.

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?

"把一句中文用户请求路由到预定义流程之一" gives a specific verb (route) plus a specific input (a single Chinese user request) and output (one of the predefined flows). What it does not do is name or characterize the target flows, so an agent knows the action but not the destination space.

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?

It explicitly states the negative case: when the flow cannot be determined, abstain (abstained=true) rather than guess. That is a genuine when-not rule with an escaping action. It stops short of saying how confident the match must be or what to do about mixed-language input.

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