Skip to main content
Glama

Contact sheet

contact_sheet

Generates a grid image of evenly spaced video frames with timestamps and an optional title bar, so you can review an entire clip at a glance and save it as a JPG.

Instructions

One grid image of evenly spaced frames with timestamp labels and a title bar — the quickest way to see a whole video at a glance (review an edit, log b-roll, find a moment, describe a clip). Optionally saved as a JPG.

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": "contact_sheet"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNoOnly look up to this time.
colsNo
pathYesAbsolute path to a local video file. ~ is expanded.
rowsNo
startNoOnly look from this time on.
titleNoAdd a title bar with file name, duration and resolution.
labelsNoDraw the timestamp on each tile.
font_fileNoFont for labels (.ttf/.otf). Defaults to a system font.
overwriteNo
save_pathNoAlso save the sheet as a JPG.
backgroundNoBackground color (ffmpeg color name or 0xRRGGBB).0x111111
tile_widthNoWidth of each thumbnail in pixels.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

B3.4/5.0
Behavior3/5

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

Annotations declare readOnlyHint=false with destructiveHint=false, so the agent already knows this writes something without being destructive. The description adds that the sheet is an image and is only saved to disk when requested, but it says nothing about what happens with save_path collisions given the undocumented overwrite parameter, or whether the image is returned inline versus as a file path.

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?

A single sentence front-loads the concrete artifact before drifting into the use-case list, and every clause earns its place. The em-dash parenthetical runs slightly long but stays scannable and contains 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?

With 12 parameters and no output schema, the description does the essential work of explaining what the returned artifact looks like and that saving is optional. It still leaves the agent guessing on return channel (inline image vs. path), overwrite behavior, and time-range semantics for start/end.

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 75%, so the baseline is 3 and the schema already carries most parameter meaning. The description reinforces the visible-behavior parameters (timestamp labels, title bar, optional JPG save), but adds nothing about start/end range semantics, cols/rows limits, or the undescribed overwrite flag.

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 names a concrete output artifact (one grid image of evenly spaced frames with timestamp labels and a title bar) plus an optional JPG save, which is far more specific than the bare name 'contact_sheet'. It does not explicitly contrast itself with siblings like make_preview, make_thumbnail, or extract_frames, so an agent must infer the distinction from the artifact described.

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?

The parenthetical use cases (review an edit, log b-roll, find a moment, describe a clip) give real when-to-use signals well matched to the grid output. However, there is no when-not guidance and no routing to alternatives such as grab_frame for a single still or extract_frames for separate files.

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