Skip to main content
Glama
Sign In
agent-video-engine

agent-video-engine

by ferdy252
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

color_preview

Compares saved color corrections at the same output frame, returning a job ID for labeled before-and-after PNG previews without altering the saved edit.

Instructions

Compare saved color corrections at one identical output frame. Returns a durable job ID; read job_get for labeled before and after PNG images. Uses the same saved edit, captions, graphics, frame and scale for both images. The before image bypasses engine color controls. Requires the engine timeline or a custom layer. Creates derived previews without changing the saved edit.

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": {
      "projectDir": "<projectDir>",
      "expectedRevision": "<expectedRevision>"
    },
    "name": "color_preview"
  }
}

Input Schema

NameRequiredDescriptionDefault
frameNo
scaleNo
projectDirYesAbsolute path of the local video project directory
expectedRevisionYesRevision returned by project_inspect. Prevents overwriting newer edits.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv3.0.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false and destructiveHint=false, and the description resolves the apparent ambiguity by stating it 'Creates derived previews without changing the saved edit.' It also discloses a non-obvious behavioral trait: 'The before image bypasses engine color controls,' which an agent could not learn from annotations or schema. Error behavior on a stale revision is left unstated.

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?

Five short sentences, front-loaded with the core action and the async handoff to job_get. Each sentence carries distinct information (job pattern, shared inputs, before-image caveat, precondition, non-destructiveness), with no filler or repetition.

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 an async job-launching tool with no output schema, it explains how results are retrieved and what is guaranteed not to change, which is the essential missing piece. It omits failure modes such as a stale expectedRevision and says nothing about whether a job can be re-polled or cancelled, the latter of which job_get/job_cancel would cover.

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 only 50%, with frame and scale undocumented in the schema. The description adds meaning by noting the same 'frame and scale' apply to both images, but it gives no defaults, ranges, or tradeoffs for those two parameters, so it only partially compensates for the coverage gap.

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 specific verb and resource ('Compare saved color corrections at one identical output frame') and clarifies the artifact produced ('durable job ID' followed by 'labeled before and after PNG images'). It does not explicitly distinguish itself from the neighboring preview_render or source_preview tools, so an agent must infer the split from the color-correction framing alone.

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?

It gives a hard precondition ('Requires the engine timeline or a custom layer') and a next step ('read job_get'), which is real routing guidance. It never states when to choose this over sibling render/preview tools, so the when-to-use guidance is implied rather than explicit.

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