Voice Coach MCP

Overview Schema Source Related Servers Discussions Admin

speech_metrics

Idempotent

Analyzes speech audio to measure pace, pauses, filler words, and pitch/volume variation, revealing delivery patterns and areas for improvement.

Instructions

Measures pace, pauses, filler words and pitch/volume variation of a speech.

Args:
    audio: audio path or a name returned by record_audio.
    language: language of the speech ("en" or "es"; filler lists exist for both).
    pause_threshold_s: minimum silence between words to count as a long pause.

Returns:
- `pace`: words, speaking_time_s, words_per_minute, wpm_excluding_long_pauses.
- `pauses`: count, total_s, max_s, per_minute and items [{t, dur, after: previous word}].
- `fillers`: total, per_minute, by_type and occurrences [{t, text}]. Ambiguous words
  ("like", "so") only count when isolated by a comma or a pause.
- `pitch`: median_f0_hz, std_semitones, range_p10_p90_semitones, monotone (std < 2 st) and
  monotone_stretches [{t, end}] over 8 s windows.
- `volume`: mean_dbfs, std_between_words_db, range_p10_p90_db, low_variation (std < 3 dB).
- `segments` of the transcript [{t, end, text}].

Input Schema

Name	Required	Description	Default
`audio`	Yes
`language`	Yes
`pause_threshold_s`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 23, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations declare idempotent, non-destructive, closed-world, but the description adds genuinely non-structured behavior: filler words like 'like'/'so' only count when isolated by a comma or a pause, and monotone/low-variation are defined by numeric thresholds. It also clarifies that audio may be a name returned by record_audio, which explains the cross-tool dependency. It omits any note on cost/runtime for audio processing, which is the one behavioral trait still missing.

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

Conciseness3/5

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

The one-line purpose is properly front-loaded and the Args block is tight. The Returns block, however, is a long enumeration of output fields that an output schema already covers, so a substantial fraction of the text does not earn its place.

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

Completeness4/5

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

All three parameters are documented, the input source ambiguity is resolved, and threshold semantics are disclosed; annotations plus the output schema carry the safety and return-shape burden. The remaining gap is operational: no indication of processing expectations or audio-format constraints for what is likely a heavy analysis call.

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% and the description fully compensates: audio is 'path or a name returned by record_audio', language is constrained to 'en' or 'es' with the note that filler lists exist for both (an enum the schema lacks), and pause_threshold_s is defined as the minimum silence between words to count as a long pause. Each parameter gains meaning beyond its bare title.

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 first sentence gives a specific verb plus the exact measured dimensions (pace, pauses, fillers, pitch/volume variation), which is far stronger than a generic 'analyze speech'. It does not, however, name the overlapping siblings analyze_pitch and transcribe, so an agent must infer that this tool subsumes rather than replaces them.

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

Usage Guidelines3/5

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

Usage is only implied by the purpose sentence – an agent can guess you call this when you want delivery metrics rather than a raw transcript. There is no explicit when-to-use/when-not, no mention of prerequisites (recording must exist first), and no routing to analyze_pitch or transcribe despite clear functional overlap.

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

Deploy Server