Skip to main content
Glama

detect_scenes

Detect visual scene cuts and shot boundaries in a video with ffmpeg's scene-change filter, especially for silent footage or screen recordings, and optionally apply results as navigable chapters.

Instructions

Detect visual scene cuts / shot boundaries in the video using ffmpeg's scene-change filter. Useful for videos without dialogue or transcripts (screen recordings, silent footage, music videos). Set to_chapters: true to immediately install the detected scenes as navigable chapters on the playing file.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "detect_scenes"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileNoOptional video file path; defaults to the playing file
thresholdNoScene change sensitivity threshold between 0.05 and 0.95 (default 0.3; lower detects more subtle cuts)
max_scenesNoMaximum number of scenes to return (1-100, default 20)
to_chaptersNoApply detected scenes as virtual chapters on the playing file

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations at all, the description carries the full behavioral burden. It does well to disclose the detection mechanism and to warn that to_chapters: true mutates the playing file by installing chapters, but it omits whether existing chapters are replaced, whether the operation is reversible, and what the detection actually returns.

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 sentences, front-loaded with the core action, with no filler or repetition. Slightly more compact phrasing could fold the usefulness sentence into the first, but nothing is wasted.

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?

Covers purpose, the mechanism, the optional mutation, and the footage types it fits, which is most of what an agent needs for a 4-parameter, all-optional tool. The remaining gap is that no output schema exists and the description never says what a detection result looks like.

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%, including defaults and directionality for threshold and max_scenes, so the baseline is 3. The description restates to_chapters' effect in nearly the same words as the schema ('navigable chapters on the playing file' vs 'virtual chapters on the playing file'), adding little beyond structured fields.

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?

States a specific verb and resource — 'Detect visual scene cuts / shot boundaries in the video' — plus the underlying mechanism (ffmpeg's scene-change filter). It hints at the differentiating case ('videos without dialogue or transcripts'), which implicitly separates it from transcript-based approaches, but never names a sibling tool outright.

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 clear usage context by listing the footage types it suits (screen recordings, silent footage, music videos) and explains the to_chapters switch as an optional follow-on action. It stops short of stating when not to use it or naming an alternative tool for dialogue-heavy videos.

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