Recognize local audio and compare the transcription against a reference script to verify spoken content matches expected dialogue.
Recognize supplied local audio and compare it with a reference script.
| Name | Required | Description | Default |
|---|---|---|---|
| request | Yes | ||
| project_root | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v1.16.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It says 'local audio' (implying file-path input, not URLs) and that a comparison against a script occurs, but discloses nothing about output shape, failure modes, required formats, or permissions.
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 well-formed sentence with the operation front-loaded and zero padding. Its brevity is efficient, though part of the reason it is short is that it omits needed detail.
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?
An output schema exists, so return values need not be explained. However, with an opaque anyOf 'request' parameter, zero schema coverage, and no annotations, an agent cannot determine what to pass or what behavioral constraints apply; the definition is too thin for this tool's complexity.
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 neither parameter is described. 'request' is an opaque anyOf(object|string) and 'project_root' is unexplained; the description only vaguely implies that audio and a reference script are involved, without mapping them to parameters.
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?
States a specific verb pair (recognize + compare) and resource (local audio vs reference script), which is enough to distinguish it from siblings like sound_qa_loudness or hyperframes_transcribe. It stops short of naming a sibling or clarifying the ASR/QA framing explicitly, but the purpose is recoverable.
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?
There is no guidance on when to use this tool versus the many other audio/transcription siblings (hyperframes_transcribe, video_ai_transcribe, sound_qa_loudness). No prerequisites, no exclusions, no alternative routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.