Skip to main content
Glama

PVQA: voice quality of a recording

pvqa_analyze
Read-only

Non-intrusive voice quality analysis (Sevana PVQA) of an uploaded WAV file: predicted MOS (1-5) and the impairments found (low SNR, noise, dead air, clipping, clicks, echo, packet-loss artifacts, ...). No reference recording is needed. report_type "extended" adds the per-interval detector table.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "upload_id": "<upload_id>"
    },
    "name": "pvqa_analyze"
  }
}

Input Schema

NameRequiredDescriptionDefault
channelNochannel to analyze, from 0 (default 0); -1 mixes all channels
upload_idYesupload_id of a WAV file
report_typeNo"basic" (default) or "extended" (adds the per-interval table)

Output Schema

NameRequiredDescriptionDefault
mosYespredicted MOS (1-5); null when the file has no speech to score
channelYes
rfactorNoshare of good intervals (0-1)
timelineNoper-interval detector values (report_type=extended only)
intervalsYes
is_silentYestrue when the file contains no signal
mos_modelNoname of the learned MOS model that produced the score
upload_idYes
impairmentsYesdetectors that fired, with their interval counts

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Beyond the readOnlyHint/idempotentHint annotations, the description discloses the method (Sevana PVQA), that it is non-intrusive, the scoring scale (MOS 1-5), the concrete impairment categories reported, and the effect of report_type extended (adds a per-interval detector table). It does not discuss runtime, cost, or failure modes for invalid/non-WAV uploads, so it stops short of full behavioral context.

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

Conciseness5/5

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

Three tight sentences, front-loaded with what the tool does, followed by the key capability (no reference needed) and the option semantics. No filler or repetition; every clause carries information.

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?

An output schema exists, so return-value explanation is not required, and the description still correctly previews MOS plus impairments. For a 3-parameter analysis tool the definition is nearly complete; the only real gap is the lack of linkage to the upload step and to sibling analysis tools.

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

Parameters3/5

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

Schema description coverage is 100%, so all three parameters are already documented. The description reinforces report_type semantics (basic default vs extended adding the per-interval table) but adds nothing about the channel parameter (0-based indexing, -1 mixes all channels) that isn't already in the schema, so baseline 3 applies.

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: a non-intrusive voice-quality analysis (Sevana PVQA) of an uploaded WAV file, returning a predicted MOS 1-5 plus detected impairments. That is concrete and distinguishable from, say, a generic analyzer, but it never names or contrasts the closely related siblings (pvqa_detector, pvqa_timeline, aqua_compare), leaving the agent to infer the split.

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?

It conveys one useful usage condition — no reference recording is required, i.e. the analysis is single-ended, unlike a comparative tool. However there is no explicit when-to-use or when-not-to-use guidance versus pvqa_detector, pvqa_timeline, or aqua_compare, and no mention of the prerequisite that the WAV must already be uploaded via create_upload to obtain an upload_id.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources