agent-video-engine

Overview Schema Source Related Servers Discussions Admin

source_preview

Inspect an original source asset before making editorial decisions: render a still or short clip that bypasses saved color, audio, and gain changes without modifying the current project.

Instructions

Inspect an original source asset before making editorial decisions. Renders a still or short source clip without changing the saved edit. Bypasses saved color controls, audio finishing and manual edit gains so it represents the original recording.

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>",
      "assetId": "<assetId>"
    },
    "name": "source_preview"
  }
}

Input Schema

Name	Required	Description	Default
`kind`	No		still
`scale`	No
`assetId`	Yes
`sourceEnd`	No
`projectDir`	Yes	Absolute path of the local video project directory
`sourceStart`	No
`expectedRevision`	Yes	Revision returned by project_inspect. Prevents overwriting newer edits.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv3.0.0Nov 6, 2026

TDQS

A3.5/5.0

Behavior4/5

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

Annotations only cover the safety triad (readOnlyHint false, destructiveHint false, openWorldHint false); the description adds real behavioral value by explaining that the output represents the original recording, un-colored and un-mixed, and that the saved edit is untouched. It does not say where the rendered still/clip is written or how the agent retrieves it, which would have earned 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?

Three tight sentences, front-loaded with the purpose, then the render scope, then the fidelity caveat. No filler and no repetition of the tool name.

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?

For a 7-parameter tool with no output schema, the description covers intent and fidelity well but leaves the output destination, cost/latency of rendering a clip, and most parameter semantics unexplained. Adequate to decide whether to call it, not adequate to call it correctly without reading the schema.

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 only 29% of 7 parameters, so the description must compensate and largely fails: 'still or short source clip' hints at the kind enum and the sourceStart/sourceEnd window, but scale, assetId semantics, and the handling of expectedRevision are never discussed. An agent still has to guess at most parameter behavior from the schema alone.

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?

Names a specific verb and resource: 'Inspect an original source asset' and 'renders a still or short source clip'. It implicitly distinguishes itself from other preview tools by stating it bypasses saved color, audio finishing and edit gains, so an agent can infer it is the raw-source counterpart to color_preview/preview_render, though no sibling is named explicitly.

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?

Provides a usage context ('before making editorial decisions') and a non-mutation guarantee, but never states when to prefer this over preview_render or color_preview, nor any prerequisites such as needing a valid revision or an indexed asset. Usage is implied rather than prescribed.

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