recognize_audio

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

Beyond the annotations, the description discloses important behavioral details: short audio uses qwen3.5-omni directly, long audio switches to fun-asr and is asynchronous, and local files are uploaded to temporary OSS. This is exactly the kind of hidden behavior an agent needs to anticipate.

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 compact, front-loads the core purpose, and presents the routing rules and return type in a scannable structure with no filler. Every sentence earns its place.

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?

Given that an output schema exists and annotations cover the safety profile, the description is complete: purpose, routing thresholds, side effect (OSS upload), asynchronous behavior, and output nature are all present. No critical decision information for an agent 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 description coverage is 100% and the schema already defines audio, task, and language. The description adds useful context about processing branches that affect audio selection and the language hint, but it does not substantially extend parameter-level meaning beyond what the schema already provides.

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 names a specific action ('识别') and resource ('本地音频或音频 URL'), and the short/long routing makes the tool's job unmistakable. It is also immediately distinguishable from sibling tools like recognize_image and recognize_video by audio modality.

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 clearly indicates this tool is for audio recognition and provides explicit condition-based routing for short vs long audio, which is strong usage context. It does not explicitly name sibling alternatives or state when not to use them, so it stops just short of a 5.

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