Skip to main content
Glama

Render GPU preview screenshots

render_preview
Read-only

Render JPEG screenshots of the live project timeline at chosen timestamps, with optional normalized crop, to visually inspect frames before exporting video.

Instructions

Render real GPU-composited JPEG screenshots of the live project timeline at specified timestamps (and optional normalized 0..1 region crop) — the Levea equivalent of ffmpeg frame extraction, showing all video layers, captions, title cards, color grades, masks, and VFX shaders. Returns native MCP image blocks so you can visually inspect the frames before calling EXPORT_VIDEO.

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": "render_preview"
  }
}

Input Schema

NameRequiredDescriptionDefault
sceneNoOptional inline scene.
regionNoOptional normalized zoom region { x, y, width, height } in 0..1 coordinates.
project_idNoProject id to render.
timestampsNoTimeline timestamps in seconds to capture (e.g. [1.0, 5.0, 12.0]).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.7.1

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that — the output is native MCP image blocks showing all composited layers, captions, grades, masks, and VFX — but says nothing about render latency, per-call limits, or what happens if the timeline is empty or timestamps out of range.

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?

Single dense sentence, front-loaded with the verb and resource, with the crop and return-format details trailing. Efficient, though the parenthetical crop clause and the long layer enumeration make it heavier than strictly necessary.

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?

Even without an output schema, the description states the return type (native MCP image blocks) which is the key unknown for this tool. All four parameters are touched and no required params exist, though defaults for omitting timestamps or project_id are unspecified.

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%, so required baseline is 3. The description reiterates the timestamps and normalized 0..1 region crop semantics that the schema already documents, adding no new syntax or constraint details beyond what the structured fields provide.

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?

Opens with a specific verb+resource: "Render real GPU-composited JPEG screenshots of the live project timeline at specified timestamps." It further distinguishes itself from EXPORT_VIDEO and grounds the metaphor in ffmpeg frame extraction, so an agent knows exactly what it gets back.

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?

Explicitly frames the use case as visual inspection "before calling EXPORT_VIDEO," which gives a clear when-to-use anchor and names an alternative. It stops short of stating when not to use it (e.g., cost/latency tradeoffs on large renders) or what to do if a render fails.

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