Transcribe local audio or video files into text via the Audio Transcriptions API, with optional model, prompt, language, and response format settings.
Transcribe a local audio/video file using the Audio Transcriptions API.
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | gpt-transcribe | |
| prompt | No | ||
| language | No | ||
| file_path | Yes | ||
| response_format | No | json |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v0.1.2Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden and provides almost nothing: no mention of size limits, supported formats, cost, latency, or whether the call is synchronous. The only behavioral signal is that the input file is local rather than already uploaded.
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 front-loaded sentence with zero filler. Nothing is redundant or buried.
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 described, but for a 5-parameter transcription tool with no annotations and 0% schema coverage, the definition omits essential operational details like format constraints, model selection guidance, and language handling.
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% across 5 parameters, so the description must compensate and largely does not. 'Local audio/video file' maps loosely to file_path, but model, prompt, language, and response_format receive no explanation of valid values or effects.
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 and resource: 'Transcribe a local audio/video file', plus names the backing API. It is clearly distinct from siblings like openai_generate_speech (TTS) or openai_create_realtime_translation_secret, though it never explicitly contrasts itself with openai_upload_file.
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 when-to-use or when-not-to-use guidance, no prerequisites, and no mention of the alternative workflow implied by the sibling openai_upload_file. The phrase 'local audio/video file' hints that file_path is a filesystem path rather than a file ID, but that is left to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.