Skip to main content
Glama

Make a GIF / looping preview

make_preview

Create a looping preview from a video section as an optimized GIF, silent MP4, or animated WebP for READMEs, Slack, client previews, or reaction clips.

Instructions

Turn a section of a video into a looping preview: an optimized GIF (custom palette, small file), a silent MP4 loop, or animated WebP. For X/Slack/Notion/GitHub READMEs, client previews, or reaction clips. Returns the first frame so you can confirm the section.

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>"
    },
    "name": "make_preview"
  }
}

Input Schema

NameRequiredDescriptionDefault
fpsNo
loopNo
pathYesAbsolute path to a local video file. ~ is expanded.
startNoWhere the preview starts.
widthNo
colorsNoGIF palette size; fewer = smaller file.
dry_runNo
durationNoLength in seconds.
overwriteNo
output_pathNoDefaults to <name>_preview.gif next to the video. Extension picks the format: .gif, .mp4, .webp.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations only declare it is a non-destructive write, so the description carries real weight here: it discloses the output formats, notes the GIF is optimized with a custom palette for a small file, and states the return value ('the first frame') in a context with no output schema. It does not explain the write side effects, e.g. how overwrite behaves or what happens when the target exists.

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 action and outputs, then use cases, then the return value. No filler and every clause contributes information an agent can act on.

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 10-parameter tool with no output schema, the description covers purpose, formats, and return value well, but leaves five parameters (fps, width, loop, dry_run, overwrite) without semantic coverage anywhere. Adequate to select and roughly invoke the tool, but not complete for correct invocation.

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 50% across 10 parameters, and the description adds only indirect meaning — 'custom palette, small file' hints at colors, and the format list corresponds to output_path extensions. It says nothing about fps, width, loop, dry_run, or overwrite, leaving half the parameters undocumented in either place.

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 ('Turn a section of a video into a looping preview') and enumerates concrete output artifacts (optimized GIF, silent MP4 loop, animated WebP), which clearly separates it from sibling tools like make_thumbnail or extract_frames that produce stills.

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 with named destinations ('X/Slack/Notion/GitHub READMEs, client previews, or reaction clips'), which tells an agent the intended scenarios. It stops short of explicit when-not-to-use guidance or naming a sibling alternative such as make_thumbnail for still images.

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