Skip to main content
Glama

Extract frames from a Playground clip

playground_video_extract_frames
Idempotent

Take the first and/or last frame of a finished clip and place each on the canvas as a Frame Grab node wired from the clip, holding a real stored image. A frame node can then feed an image → video node as first_frame or last_frame (playground_canvas_apply_operations connect with role). Only "first" and "last" are supported; a timestamp in seconds is refused. Free: no credits are spent. Revision checked and idempotent; it can take up to two minutes. Returns created frame node IDs, image URLs, revision and Playground URL.

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": {
      "projectId": "<projectId>",
      "videoNodeId": "<videoNodeId>",
      "expectedRevision": "<expectedRevision>",
      "idempotencyKey": "<idempotencyKey>",
      "positions": "<positions>"
    },
    "name": "playground_video_extract_frames"
  }
}

Input Schema

NameRequiredDescriptionDefault
positionsYesFrame positions to extract: first, last, or timestamps in seconds from the video start.
projectIdYesID of the Playground project chosen for this task; obtain it from project creation, an explicit project link or current context.
videoNodeIdYesExisting canvas video node ID containing the source video.
idempotencyKeyYesUnique key for this request; reuse only when retrying the identical request after a lost response. Use a new key after quoting or changing inputs.
expectedRevisionYesCurrent canvas revision from canvas_read; on revision_conflict, read again and rebuild the change.

Output Schema

NameRequiredDescriptionDefault
nextYesSuggested next action; it does not authorize spending.
framesYes
nodeIdsYes
replayedYes
revisionYes
canvasUrlYes
videoNodeIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Beyond the annotations (readOnly=false, destructive=false, idempotent=true) it discloses cost (free, no credits spent), latency (up to two minutes), revision checking with idempotency behavior, and the return contents — exactly the behavioral context annotations cannot convey.

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?

The three dense sentences are front-loaded with the core action and constraints, with no filler. It is slightly packed, but every clause (constraint, downstream wiring, cost, latency, revision, returns) carries operational information.

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 mutating, revision-checked canvas operation the essentials are covered: idempotency, expected revision conflicts, cost, latency, and resulting node/image outputs. The one gap is the unresolved conflict over numeric timestamps, which leaves an agent uncertain whether a numeric position will work.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline would be 3, but the description actively contradicts the schema's `positions` parameter, which explicitly accepts numeric timestamps in seconds (0–3600) with a description saying timestamps from video start are valid, while the text says a timestamp is refused. This is misleading rather than additive for the one parameter that most needs clarity.

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 ("Take the first and/or last frame of a finished clip") and states the resulting artifact (a Frame Grab node wired from the clip holding a real stored image), which an agent can distinguish from sibling tools like playground_video_trim or playground_video_analyze.

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 the acceptance constraint (only "first" and "last"; timestamps refused) and the downstream pattern (feed into an image→video node as first_frame/last_frame via playground_canvas_apply_operations connect with role). It does not explicitly say when to prefer this over video_trim or analyze, but the context for correct use is clear.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.