Transcribe speech from a local audio file, automatically detecting the format from its file extension.
Recognize speech from a local audio file. Auto-detects format from extension.
| Name | Required | Description | Default |
|---|---|---|---|
| language | No | Recognition language (ru-RU, en-US, kk-KZ) | ru-RU |
| file_path | Yes | Absolute path to the audio file to recognize | |
| sample_rate | No | Sample rate in Hz — required for headerless .pcm/.alaw/.ulaw files (e.g. 16000, 8000) |
Changes observed during successful MCP inspections.
v1.2.0Input schema / properties / sample_rateAdded value: +{
+ "description": "Sample rate in Hz — required for headerless .pcm/.alaw/.ulaw files (e.g. 16000, 8000)",
+ "exclusiveMinimum": 0,
+ "type": "integer"
+}v1.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of disclosing behavior. It reveals one key behavior—auto-detection of format from the extension—but does not mention side effects (none apparent, but not stated), error handling for missing files or unsupported formats, or the fact that it is a read-only operation. Some transparency is present, but significant behavioral details are omitted.
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 description is two sentences with zero waste. The primary purpose is stated first, and the key detail about auto-detection is injected naturally. It is succinct and well-structured, making it easy for an agent to parse quickly.
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 explains the main function and a key feature, but it does not mention the output format (e.g., recognized text, confidence scores) or any prerequisites like file existence or network access. Since there is no output schema to fill this gap, the description is only partially complete. An agent might be unclear about what to expect as a result, though the tool name and verb 'Recognize' offer some hint.
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 fully documents all three parameters (file_path, language, sample_rate) with clear descriptions and defaults. The description adds little beyond the schema: it implies that file_path should have an extension (due to auto-detection) and that sample_rate is needed for headerless files, but these are already inferable from the schema's 'required for headerless' note. Since schema coverage is 100%, the baseline of 3 is appropriate.
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 uses the specific verb 'Recognize' and clearly identifies the resource 'speech from a local audio file.' It also mentions auto-detection of format, which distinguishes it from a generic recognition tool and from sibling tools like recognize_speech that may handle other input sources. The purpose is unmistakable.
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?
The statement 'Auto-detects format from extension' provides implicit guidance on when to use this tool (when the file extension indicates the format) and when additional parameters like sample_rate may be needed (headerless files). However, it does not explicitly compare with sibling tools such as recognize_speech, leaving some ambiguity about when to prefer one over the other. The guidance is clear but not exhaustive.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.