speak_with_voice

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

With no annotations provided, the description carries the full burden. It discloses the output type ('可下载的音频 URL'), the billing model ('按文本长度计费(tts 档)'), and the independence from character/drama context. It doesn't mention async behavior or URL lifecycle, but the key operational traits are covered.

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?

Two compact sentences, each earning its place: the first states the core action and result, the second covers use cases, exclusions, and billing. The most important information is front-loaded 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 two-parameter tool with fully documented schema, the description explains the return value, standalone usage context, and cost model. It omits explicit alternative routing (e.g., generate_tts) and async behavior, but an agent can likely invoke it correctly with the provided information.

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?

The input schema already documents both parameters thoroughly, including the voice_id source ('来自 clone_voice / list_voices 的 voice_id(形如 lib:12)') and the text length cap. The description adds only a general '任意文本' note and billing-by-length, which slightly reinforces text usage but does not significantly exceed schema coverage.

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 opens with a specific action ('让某个音色说一段任意文本'), a concrete resource (a cloned voice), and an explicit outcome ('返回可下载的音频 URL'). It also distinguishes itself from character/drama-bound voice tools by stating '不需要角色、不需要剧目' and clarifying the standalone post-clone use case.

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 gives explicit when-to-use guidance: verify a cloned voice ('克隆完先用它验收音色像不像') or take audio elsewhere ('直接把音频拿去别处用'). It also states an exclusion ('不需要角色、不需要剧目'), though it does not name specific alternative tools such as generate_tts or assign_voices.

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