Skip to main content
Glama
Sign In
Foldline

Foldline

by alireza12t
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

Check voice lines with speech-to-text

check_voice
Read-only

Verifies voiceover recordings against script text by running Whisper on each WAV, saving word timestamps, and returning only failed lines with a count.

Instructions

Runs Whisper over every .wav and compares it with the text. Writes words.json (word timestamps). Returns only the lines that failed and a count.

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": {
      "lines_json": "<lines_json>",
      "voices_dir": "<voices_dir>"
    },
    "name": "check_voice"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNo
lines_jsonYesThe lines.json used for the voice.
voices_dirYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.9/5.0
Behavior1/5

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

The description states the tool 'Writes words.json (word timestamps)', a filesystem side effect, while the annotations declare readOnlyHint=true. The description is the accurate side here, but as written the definition contradicts the structured safety hint an agent would rely on to decide whether it is safe to call in a read-only context.

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?

Three short sentences, front-loaded with the action and followed by the side effect and the return shape; nothing is padded. The '<id>.wav' shorthand assumes the caller already knows the naming convention, which is the only small friction.

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?

With no output schema, the description usefully covers the return value ('only the lines that failed and a count') and the artifact it creates. What is missing is the lang parameter and any note about what happens to pre-existing words.json files on re-run.

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 coverage is only 33%. The description implicitly clarifies two of three params: voices_dir holds the <id>.wav files and lines_json supplies the reference text. The 'lang' enum (en/zh/auto) is never mentioned, so that parameter's meaning and default behavior are undocumented in both places.

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?

Names a specific verb and resource: runs Whisper over every <id>.wav and compares the transcript against the text, and it says what it returns (failed lines plus a count). This is clearly distinguishable from make_voice or check_reading, though it never explicitly contrasts itself with the check_reading sibling.

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

Usage Guidelines2/5

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

The description explains the mechanics but gives no when-to-use guidance: nothing says whether this is a post-generation verification step, whether it should run before make_subtitles, or what to do with the failure list. The agent must infer the workflow position from the tool name.

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

Deploy Server

Other Tools