Skip to main content
Glama

Make a thumbnail

make_thumbnail

Export platform-sized thumbnails from a video by auto-picking the sharpest, best-exposed frame or using a specific timestamp, then crop to the target aspect ratio.

Instructions

Export a thumbnail sized for a platform (YouTube 1280x720, Reels/TikTok/Shorts cover 1080x1920, Instagram grid 3:4, feed 4:5, square, X, LinkedIn). Give at to use a specific frame, or leave it out and the tool samples the video, rejects black/white/flat frames, and picks the sharpest, best-exposed one — returning the top candidates so you can choose a different one. Crops to the aspect ratio with an adjustable anchor.

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_thumbnail"
  }
}

Input Schema

NameRequiredDescriptionDefault
atNoUse the frame at this time instead of auto-picking.
endNoOnly look up to this time.
pathYesAbsolute path to a local video file. ~ is expanded.
startNoOnly look from this time on.
widthNoCustom width (overrides preset).
heightNoCustom height (overrides preset).
presetNoSize preset: youtube, youtube_shorts, instagram_reels_cover, instagram_grid, instagram_feed, tiktok_cover, square, x, linkedinyoutube
qualityNo
anchor_xNoHorizontal crop anchor: 0 keeps the left edge, 1 the right.
anchor_yNoVertical crop anchor: 0 keeps the top, 1 the bottom.
overwriteNo
candidatesNoFrames to evaluate when auto-picking.
output_pathNoDefaults to <name>_<preset>_thumb.jpg next to the video. .jpg, .png or .webp.
show_candidatesNoReturn this many runner-up frames as small images.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=false and destructiveHint=false, so the description carries real weight here and delivers: it discloses the auto-pick heuristics (rejects black/white/flat frames, picks sharpest and best-exposed) and that runner-up candidates are returned for reselection. It omits file-write semantics — notably that an existing file at output_path is not replaced unless `overwrite` is set — which is the main behavioral gap 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.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with the resource and platform targets, then mode selection, then crop behavior. The parenthetical preset/dimension list is dense but pays for itself since the schema lists preset names without sizes; minor run-on feel in the auto-pick sentence.

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?

For a 14-parameter tool with no output schema, the description covers the two important decisions (which frame, which size/crop) and the fact that multiple candidates come back. Remaining gaps are secondary parameters — overwrite behavior and output naming conventions — that the schema partially covers.

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 86%, so a 3 would be the baseline; the description earns the extra point by supplying meaning the schema lacks, namely the pixel dimensions behind each preset (YouTube 1280x720, cover 1080x1920, etc.) and explaining that crop anchoring is adjustable. It still leaves `overwrite`, `quality`, and `start`/`end` unexplained in prose.

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 ("Export a thumbnail") and enumerates the target platforms and their dimensions, which an agent cannot infer from the name alone. It also clarifies the two operating modes (explicit frame via `at` vs. auto-pick), which is the main axis distinguishing it from sibling frame tools such as grab_frame, though it never names those siblings explicitly.

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 conditional guidance: "Give `at` to use a specific frame, or leave it out and the tool samples the video" — an agent can decide the mode without reading the schema. It stops short of naming alternatives or stating when a different tool (e.g. grab_frame) would be preferable, so it is clear context rather than full routing.

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