mistral_transcribe_audioTranscribe audio files to text with Voxtral by providing Base64-encoded audio and a filename. Use it to convert speech from recordings into written transcripts.
Transcribe audio files using Voxtral.
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | Model | voxtral-mini-2507 |
| prompt | No | Transcription guidance | |
| filename | Yes | Audio filename | |
| language | No | Language code | |
| file_content | Yes | Base64-encoded audio |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive, open-world behavior, so the safety profile is covered. The description adds no behavioral context beyond restating the operation: no mention of latency, synchronous vs async return, or whether base64 audio must be a specific format/size.
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 compact sentence with no redundancy, front-loaded with the verb. However, it is arguably too terse given the missing usage and behavioral 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?
For a 5-parameter transcription tool with no output schema, the description should explain output shape (e.g., transcript text vs structured segments) and key constraints. Instead it provides only a bare operation statement, leaving significant gaps for an agent to call it correctly.
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 all 5 parameters are documented in the schema itself. The description adds no syntax, format, or constraint detail (e.g., accepted language codes, base64 encoding expectations) beyond what the schema provides. Baseline 3 applies.
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 clear verb (Transcribe) and resource (audio files), and names the underlying engine (Voxtral). It is differentiable from siblings like mistral_ocr or mistral_classify_text, though it says nothing about output format or supported audio types.
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 use this versus alternatives (e.g., mistral_ocr for text-in-image). No mention of prerequisites, file size limits, or language handling. The agent is left to infer everything about invocation context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.