Skip to main content
Glama

WritersLogic business agents

subtitle-lint

Subtitle lint: SRT and WebVTT overlaps, duration, reading speed, line length — Parses an SRT or WebVTT file (up to 400000 characters, 4000 cues) and checks every cue for an agent about to deliver or burn in captions: end after start, overlaps and out-of-order cues, minimum gap, minimum and maximum duration, lines per cue, characters per line and characters per second (markup tags are not counted). Rules come from a named profile (netflix-en-adult, netflix-en-children, values

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": {
      "text": "<text>"
    },
    "name": "subtitle-lint"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesThe whole .srt or .vtt file.
customNoYour own rules; these override profile values.
formatNoDefault: vtt if the text starts with WEBVTT, else srt.
profileNonetflix-en-adult: 42 chars/line, 2 lines, 20 cps, 5/6 s to 7 s, 2-frame gap. netflix-en-children: same at 17 cps.
frameRateNoNeeded to turn a minimum gap in frames into milliseconds.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does substantial work: it declares hard input limits (400000 characters, 4000 cues), the exact rule set applied, that markup tags are excluded from character counts, and that rules come from a named profile with custom overrides. The main gap is that it never says what the tool returns or whether findings are errors versus a report, which matters for a validation tool.

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?

Purpose and checks are front-loaded and densely packed, but the final parenthetical is truncated mid-thought ('netflix-en-adult, netflix-en-children, values'), leaving an incomplete clause that wastes space and reads as broken output. The long single run-on sentence also makes scanning harder than a short bulleted enumeration would.

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

Completeness3/5

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

The input side is well covered for a 5-parameter tool with a nested overrides object, including limits and precedence of custom rules. But with no output schema, the description owes the caller a notion of the return shape (list of violations? severity? counts?), and it never provides one; the trailing truncation further undercuts completeness.

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 100%, so baseline is 3; the parameter descriptions already explain the profile values, format auto-detection, frameRate purpose, and that custom overrides profiles. The description adds only the 'markup tags are not counted' nuance relevant to cps and repeats the profile names, so it stays at baseline rather than adding new meaning.

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 action (parses an SRT/WebVTT file and checks every cue) against a specific resource, and enumerates the checks: end-after-start, overlaps, out-of-order cues, gaps, min/max duration, lines per cue, chars per line, chars per second. That clearly separates it from the other lint siblings (dockerfile-cache-lint, jwt-lint) which operate on entirely different artifacts.

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?

Gives a concrete use context: 'for an agent about to deliver or burn in captions,' which tells the caller when this applies. It stops short of naming alternatives or stating when not to use it (e.g. when a file is already validated or is not SRT/VTT), so it is clear but not exclusionary.

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