Voice Coach MCP

Overview Schema Source Related Servers Discussions Admin

assess_pronunciation

Idempotent

Compare spoken English with the expected text to score pronunciation and pinpoint phoneme substitutions, deletions, insertions, and missed words.

Instructions

Compares the pronounced phonemes with the expected ones for a text read aloud (English).

Args:
    audio: audio path or a name returned by record_audio (up to 60 s; short sentences work best).
    expected_text: the exact text that was read.
    language: "en-US" (default) or "en-GB".

Returns `summary` (overall_score 0–100, words_with_errors, error counts by type,
frequent_confusions expected→detected) and `words`: word, score, t (s) and, when there are
errors, expected/detected in IPA and errors [{type: substitution|deletion|insertion,
expected, detected}]; `missing` when the word was not said. `phonemes` holds both full
sequences. Word score = 100·(1 − (S + D + 0.5·I)/expected phonemes). Allophonic variants
(flap, schwa, linking r) do not count as errors. The text_mismatch warning means a
different text was probably read. Backend: local wav2vec2, or Azure when
VOICE_COACH_PRONUNCIATION_BACKEND=azure (then the audio is sent to Azure).

Input Schema

Name	Required	Default
`audio`	Yes
`language`	No	en-US
`expected_text`	Yes

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 23, 2026

TDQS

A4.5/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations, the description discloses important behavior: audio is sent to Azure only when the backend environment variable is set, the scoring formula is given, allophonic variants are excluded from errors, and text_mismatch indicates a likely wrong text. These are substantial operational and privacy-relevant details.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded and well organized, with arguments first, then return details and behavioral notes. It is somewhat dense and explains return fields despite an output schema existing, but the information largely earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the output schema, annotations, and three-parameter schema with no descriptions, the description is complete enough to call the tool correctly. It covers inputs, output structure, scoring behavior, warnings, and backend-dependent privacy implications.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry parameter meaning. It fully documents all three parameters: audio source and duration, exact expected text, and language values en-US and en-GB.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: it compares pronounced phonemes with expected phonemes for English text read aloud. The scope and purpose are clear, but it does not explicitly distinguish itself from siblings such as transcribe or speech_metrics.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear usage context: audio can be a path or a name returned by record_audio, recordings up to 60 seconds work, and short sentences work best. It also explains the text_mismatch warning, though it does not explicitly say when to prefer this tool over transcribe or speech_metrics.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server