Extract speech from a local audio recording and save the isolated voice track, not a music stem separation. Use it to clean dialogue audio with cost controls.
Isolate speech from a local audio recording. This is not a music stem separator.
| Name | Required | Description | Default |
|---|---|---|---|
| filename | Yes | ||
| allow_paid | No | ||
| input_path | Yes | ||
| allow_unknown_cost | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden but discloses little beyond the local input and functional scope. It does not explain where output is written, whether the source remains unchanged, supported inputs, or the cost implications suggested by allow_paid and allow_unknown_cost.
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 two short sentences are front-loaded and contain no wasted wording. The second sentence earns its place by preventing a plausible confusion with the music-stem tools.
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?
The description is sufficient for high-level tool selection but not for confident invocation. With no annotations or output schema to fill the gaps, the undocumented output filename behavior and cost-control flags are substantial omissions for a four-parameter audio-processing tool.
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 0%, and the description only indirectly clarifies that input_path should identify a local audio recording. It provides no semantics for filename, allow_paid, or allow_unknown_cost, leaving most invocation details and the potentially important cost controls undocumented.
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 specifies the operation ("Isolate speech"), the resource ("a local audio recording"), and an explicit boundary with music stem separation. This clearly distinguishes its role from siblings such as separate_music_stems and extract_music_stems, even without naming 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 a clear use case and an explicit when-not condition: use it for speech isolation, not as a music stem separator. It would be stronger if it directed music-separation requests to a specific sibling or mentioned any input prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.