Imports reference audio from a local path or Base64 string (20 MB max, 1–60 seconds) to create a reusable voice and returns a voiceId.
导入参考音频，返回 voiceId。传 path（本机音频文件路径，常见格式自动转换）或 Base64 编码的 audio，限 20 MB、1–60 秒
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | 音色名称 | |
| path | No | 本机音频文件路径，仅 yovoice mcp（stdio）可用 | |
| audio | No | 参考音频的纯 Base64 字符串，不含 data URL 前缀 |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations at all, the description carries the full burden; it does disclose the return value (voiceId), automatic format conversion, and size/duration caps — solid for an import tool. It omits whether the upload persists permanently, what permissions are needed, what happens on failure (e.g. audio too long), and whether name is required for later reference.
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?
A single dense sentence that front-loads purpose, then return value, then accepted inputs, then limits — every clause carries information. It is slightly run-on with multiple parentheticals, but there is 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 zero-required-parameter mutation tool with no annotations and no output schema, the description is adequate but leaves gaps: the role of the optional 'name' parameter and its default behavior, failure modes, and whether repeated uploads create new voices are all unstated.
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, but the description adds genuine value the schema lacks: it states that path and audio are alternatives (the schema marks neither required and has no oneOf), which prevents an agent from omitting both. It also reiterates the limits applying to the audio payload, which the schema does not encode.
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 verb+resource ('导入参考音频') and states the return value ('返回 voiceId'), which is more than most import tools offer. It is clearly distinguishable from siblings like list_voices, generate, or render_score, though it does not explicitly name them.
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 the two input modes (path or Base64 audio) and hard limits (20 MB, 1–60 s), which is useful operational guidance. However, it never says when to prefer this tool over alternatives, nor any prerequisites such as auth, quota, or whether an existing voice with the same name conflicts.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.