Generates melodic singing audio from prewritten target metadata using SoulX-Singer, converting structured pitch and duration data into a rendered vocal track.
用 SoulX-Singer 根据已写好的目标元数据生成带旋律的歌声。
| Name | Required | Description | Default |
|---|---|---|---|
| device | No | auto | |
| control | No | score | |
| auto_shift | No | ||
| pitch_shift | No | ||
| output_format | No | mp3 | |
| prompt_wav_path | No | ||
| normalize_loudness | No | ||
| prompt_metadata_path | No | ||
| target_metadata_path | Yes |
Changes observed during successful MCP inspections.
v0.3.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
There are no annotations, so the description carries the full behavioral burden, yet it says nothing about that this is a local model inference (GPU/CPU), that it can be slow, whether output is overwritten, or how the produced audio is returned. It only reveals the underlying model name and the metadata precondition.
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 with no filler, so it is concise, but it is concise to the point of under-specification. For a tool with 9 parameters and no schema documentation, that brevity is a liability rather than a virtue.
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 9 parameters, no annotations, no output schema, and zero schema descriptions, the one-line description falls well short. An agent would not know how to set control or whether a prompt is required to clone a voice.
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 schema has 9 parameters, but none have descriptions and the coverage is 0%; the description only implicitly references target_metadata_path. Important parameters such as control (score vs melody), prompt_wav_path/prompt_metadata_path (voice cloning references), pitch_shift, and output_format are left entirely unexplained.
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 states a specific verb and resource: generate melodic singing (带旋律的歌声) from pre-written target metadata using SoulX-Singer. An agent can distinguish this task from speak/speak_segments (speech) and infer a difference from sing_notes, though it never explicitly names or contrasts with those siblings.
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?
No guidance on when to choose sing_metadata over sing_notes, no prerequisites for what 'pre-written target metadata' means or how to obtain it, and no mention of when to use a prompt WAV/metadata. The only implied condition is that metadata must already exist.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.