Skip to main content
Glama

frame_contact_sheet

Samples evenly spaced video frames into a single tiled JPEG with exact timestamps, enabling you to survey visual changes across a time range in one call.

Instructions

Sample a grid of frames (cols × rows) evenly across a time range of the video and return a single tiled JPEG image plus the exact timestamp of every cell. Ideal for surveying what visually happens across a video or section in one multimodal tool call instead of calling describe_frame a dozen times.

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": "frame_contact_sheet"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNoEnd time in seconds (default: file duration)
colsNoGrid columns (1-6, default 4)
fileNoOptional video file path; defaults to the playing file
rowsNoGrid rows (1-6, default 3)
startNoStart time in seconds (default 0)
max_edgeNoTarget sheet width in pixels (256-2048, default 1280)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

No annotations are supplied, so the description carries the full burden, and it does disclose the key behaviors: frames are sampled evenly, the result is one tiled JPEG, and per-cell timestamps are returned. It leaves out edge behavior (what happens if start exceeds duration or start > end) and any performance/cost characteristics of large grids, which keeps it from a 5.

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, no filler: the first defines the operation and its output, the second justifies it against the alternative. The core capability and return value are front-loaded.

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 six-parameter, all-optional tool with full schema coverage and no output schema, the description covers what the tool produces and why to choose it. Remaining gaps are minor: timestamp format, behavior on invalid ranges, and how cells map to grid positions in the returned image.

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 100%, with defaults and ranges documented for every parameter, so the baseline is 3. The description reinforces the cols × rows grid concept and that start/end define the sampled time range, but adds no format or constraint detail beyond what the schema already states.

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?

The description names a specific verb and resource ('Sample a grid of frames... evenly across a time range') and states the return artifact ('a single tiled JPEG image plus the exact timestamp of every cell'). It also explicitly contrasts itself with the sibling describe_frame, so an agent can distinguish the two without opening either schema.

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?

It states a clear use condition ('Ideal for surveying what visually happens across a video or section in one multimodal tool call') and names the alternative it replaces ('instead of calling describe_frame a dozen times'). It stops short of explicit when-not guidance, e.g. that describe_frame should be used when fine-grained inspection of a single moment is needed, and says nothing about cost or limits on grid density.

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