Skip to main content
Glama

Extract frames to a folder

extract_frames

Save video stills to a folder at fixed intervals, by frame count, per detected scene, or at exact timestamps for b-roll, storyboards, carousels, or feeding frames to other tools.

Instructions

Save stills to a folder: every N seconds, N evenly spaced frames, one per detected scene, or at exact timestamps. Files are named with their timecode. Good for b-roll stills, storyboards, social carousels or feeding frames to other tools.

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": {
      "path": "<path>",
      "output_folder": "<output_folder>"
    },
    "name": "extract_frames"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNoOnly look up to this time.
modeNocount
pathYesAbsolute path to a local video file. ~ is expanded.
countNomode=count: how many evenly spaced frames.
startNoOnly look from this time on.
timesNomode=timestamps: exact times.
widthNoResize to this width (keeps aspect). Default: full resolution.
formatNojpg
prefixNoFile name prefix; defaults to the video's name.
overwriteNo
max_framesNo
output_folderYesFolder to write into (created if missing).
scene_thresholdNomode=scenes: sensitivity.
interval_secondsNomode=interval: seconds between frames.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.6/5.0
Behavior3/5

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

The annotations already declare readOnlyHint=false and destructiveHint=false, so the agent knows this writes files without flagging destruction. The description usefully adds that files are named by timecode and that output goes into a folder, but it omits collision/overwrite semantics and what happens on existing files, which matters for a write tool.

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?

Two sentences, front-loaded with the operative mode enumeration and followed by audience examples. No redundant restatement of the tool name and no filler.

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?

For a 14-parameter write tool with no output schema, the definition covers mode selection and file naming but leaves the return value (list of written paths? count?), overwrite/collision behavior, and resizing/format interaction unstated. Adequate but not complete for a tool of this complexity.

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?

With 14 parameters at 71% schema coverage, the description adds real meaning by mapping each mode to its driving parameter ('every N seconds' → interval_seconds, 'N evenly spaced frames' → count, 'one per detected scene' → scene_threshold, 'exact timestamps' → times). That mapping helps the agent choose the right mode and companion argument, though it does not touch width, format, prefix, or max_frames.

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 uses a concrete verb and resource ('Save stills to a folder') and enumerates the four selection strategies: interval, count, scene detection, and exact timestamps. It is unambiguous about what the tool produces. It stops short of differentiating itself from the sibling 'sample_frames', so it does not fully earn a 5.

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 offers use-case guidance ('b-roll stills, storyboards, social carousels, feeding frames to other tools') but never states when to pick this tool over an alternative such as sample_frames or grab_frame, nor any exclusions. Usage is implied by the modes and examples rather than by explicit routing rules.

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