Skip to main content
Glama

Text Analysis & Cleanup Tools (Tanod)

convert_subtitles

Read-onlyIdempotent

utilpeek: Convert SRT, WebVTT and JSON subtitles; scale or shift timing. To make subtitles from audio use transcribe_audio. Returns SRT, WebVTT or JSON segments [{start, end, text}] in seconds, with optional timing scale and shift. Cue bounds and WebVTT inline timestamps map to round(ms * time_scale) + shift_ms, ties to even. At most 1,000,000 characters and 10,000 cues. Malformed input is a 422, not charged. Starts clamp at 0; with a negative shift, cues ending at or before 0 are dropped. Times past 99:59:59.999 are refused. Typically under 0.3 s. Price: USD 0.002. Free: 10 utilpeek calls per IP per UTC day. Docs: https://tanod.dev/learn/subtitle-converter-api.html

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": {
      "to": "<to>"
    },
    "name": "convert_subtitles"
  }
}

Input Schema

NameRequiredDescriptionDefault
toYesOutput format: srt (SubRip), vtt (WebVTT) or json (a list of {start, end, text}, seconds).
contentNoThe SRT or WebVTT file as text (at most 1,000,000 characters, 10,000 cues). The format is detected from a WEBVTT header unless from_format is given. Use this or segments.
segmentsNoA JSON segment list [{start, end, text}] in seconds, as /v1/audio/transcribe returns it. Use this or content.
shift_msNoTime shift in milliseconds, after scaling (negative = earlier; cues ending at or before 0 are dropped).
time_scaleNoTiming multiplier, 0.5 to 2.0; default 1. Cue bounds and WebVTT inline timestamps become round(ms * time_scale) + shift_ms; ties round to even.
from_formatNoInput format check: content is srt or vtt, segments are json.

Output Schema

NameRequiredDescriptionDefault
toNo
cuesNo
fromNo
errorNoOnly on an error result: an object {code, message}, or the reason string of an x402 PaymentRequired object.
outputNo
droppedNo
durationNo
segmentsNo
shift_msNo
operationNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / shift_ms / description
      Previous value: -"Time shift in milliseconds for every cue (negative = earlier; a cue that ends before 0 is dropped)."New value: +"Time shift in milliseconds, after scaling (negative = earlier; cues ending at or before 0 are dropped)."
    • addedInput schema / properties / time_scale
      Added value: +{
      +  "default": 1,
      +  "description": "Timing multiplier, 0.5 to 2.0; default 1. Cue bounds and WebVTT inline timestamps become round(ms * time_scale) + shift_ms; ties round to even.",
      +  "maximum": 2,
      +  "minimum": 0.5,
      +  "type": "number"
      +}
  2. Changed15 schema fields changed
    • removedInput schema / $defs / SubtitleSegment / properties / end / title
      Removed value: -"End"
    • removedInput schema / $defs / SubtitleSegment / properties / start / title
      Removed value: -"Start"
    • removedInput schema / $defs / SubtitleSegment / properties / text / title
      Removed value: -"Text"
    • removedInput schema / $defs / SubtitleSegment / title
      Removed value: -"SubtitleSegment"
    • removedInput schema / properties / content / default
      Removed value: -null
    • removedInput schema / properties / content / title
      Removed value: -"Content"
    • removedInput schema / properties / from_format / default
      Removed value: -null
    • changedInput schema / properties / from_format / description
      Previous value: -"Optional input format check: content is srt or vtt, segments are json."New value: +"Input format check: content is srt or vtt, segments are json."
    • removedInput schema / properties / from_format / title
      Removed value: -"From Format"
    • removedInput schema / properties / segments / default
      Removed value: -null
    • removedInput schema / properties / segments / title
      Removed value: -"Segments"
    • removedInput schema / properties / shift_ms / title
      Removed value: -"Shift Ms"
    • removedInput schema / properties / to / title
      Removed value: -"To"
    • removedInput schema / title
      Removed value: -"convert_subtitlesArguments"
    • removedOutput schema / properties / segments / items
      Removed value: -{
      -  "properties": {
      -    "end": {
      -      "type": [
      -        "number",
      -        "null"
      -      ]
      -    },
      -    "start": {
      -      "type": [
      -        "number",
      -        "null"
      -      ]
      -    },
      -    "text": {
      -      "type": [
      -        "string",
      -        "null"
      -      ]
      -    }
      -  },
      -  "type": [
      -    "object",
      -    "null"
      -  ]
      -}
  3. Added

TDQS

A4.6/5.0
Behavior5/5

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

Goes well past the annotations, which only declare read-only/idempotent/non-destructive. It discloses hard limits (1,000,000 chars, 10,000 cues), error semantics ('Malformed input is a 422, not charged'), clamping and cue-drop behavior under negative shift, the 99:59:59.999 ceiling, typical latency, price, and free-tier quota per IP per UTC day.

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?

Front-loaded with purpose, then constraints, then cost and limits in descending priority; nearly every clause carries operational information. Slightly overpacked as continuous prose (pricing, quota, latency, docs URL in one block) and the 'utilpeek:' prefix is low-value filler.

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?

For a 6-parameter tool with an output schema, everything an agent needs is present: format matrix, mutual exclusivity of content vs segments, limits, error behavior, and timing math. Return shape is additionally restated, so no inference is required before calling.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline would be 3, but the description adds behavior the schema does not fully spell out: starts clamp at 0, cues ending at or before 0 are dropped under negative shift, and out-of-range times past 99:59:59.999 are refused. The tie-to-even rounding rule is largely a restatement of the time_scale schema text.

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

Purpose5/5

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

States a specific verb and resource ('Convert SRT, WebVTT and JSON subtitles; scale or shift timing') and enumerates the formats on both sides of the conversion. It also names the sibling-like alternative (transcribe_audio) for the adjacent-but-different job, so an agent can place it precisely.

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?

Explicitly routes the audio-to-subtitle case to transcribe_audio, which is the main ambiguity an agent would face, and the input-side options (content vs segments) are framed as alternatives. It does not enumerate when-not conditions for timing-only operations, but the context is clear enough to select the tool correctly.

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.