agent-video-engine

Overview Schema Source Related Servers Discussions Admin

preview_render

Render a still frame or short moving preview of the current video edit, including full mixed audio for short previews. Returns a durable job ID; use job_get to retrieve results and audio warnings.

Instructions

Render a still frame or short moving preview of the current edit. Enabled audio finishing uses the full project mix so short previews retain the same settings and master level as the final export. Returns a durable job ID. Use job_get for the result, audio measurements and any peak-limited target warnings.

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": "preview_render"
  }
}

Input Schema

Name	Required	Description	Default
`fit`	No
`kind`	No		still
`frame`	No
`scale`	No
`preset`	No
`draftId`	No
`toFrame`	No
`revision`	No
`fromFrame`	No
`projectDir`	Yes	Absolute path of the local video project directory
`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

B3.4/5.0

Behavior4/5

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

Annotations only declare a non-destructive, non-read-only, closed-world write; the description adds real behavioral context: the call is asynchronous and returns a durable job ID, audio finishing uses the full project mix so preview levels match the master export, and peak-limited target warnings surface via the job. It does not state cost, latency, or what a failed render leaves behind.

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?

Three sentences, front-loaded with the capability, then async semantics, then the next-step routing. Tight and well ordered, with no filler, though it spends length on audio mastering nuance while leaving core parameters untouched.

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 an 11-parameter async job tool with no output schema, the description correctly covers the job/polling lifecycle and where results and warnings appear. It is incomplete on the parameter space, and it does not explain what expectedRevision failing means, which matters for a revision-guarded render.

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 description coverage is only 18% across 11 parameters, so the description carries the burden, yet it never explains kind, frame, fromFrame/toFrame, scale, preset, fit, draftId, or revision. Only the vague "still frame or short moving preview" hints at the kind enum; the rest is left entirely to bare schema keywords.

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?

"Render a still frame or short moving preview of the current edit" gives a specific verb and resource plus the two output modes. It implicitly separates the tool from export_render (final export) and source_preview/color_preview, but never names those siblings 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?

It tells the agent the follow-up step (use job_get for the result) and contrasts preview against final export, which is useful sequencing guidance. It gives no explicit when-not condition or named alternative for the case where the user wants the final render instead of a preview.

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