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

agent-video-engine

by ferdy252
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

draft_stage

Prepare and validate video edits as a draft without changing the saved project, then render the preview and apply the reviewed state.

Instructions

Prepare a validated edit without changing the saved project. Render it using preview_render with draftId, then apply the exact reviewed state with draft_apply.

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>",
      "operations": "<operations>"
    },
    "name": "draft_stage"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNo
operationsYes
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

A4.2/5.0
Behavior4/5

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

Annotations only tell the agent this is non-read-only but non-destructive; the description adds the crucial fact that nothing is persisted ('without changing the saved project') and that validation happens at stage time. What it omits is failure behavior — what a validation rejection looks like and how long a staged draft survives before it must be applied.

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?

Two sentences, zero filler, and the non-persistence guarantee is front-loaded ahead of the downstream workflow. Every clause earns its place.

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?

The lifecycle and output identity (draftId) are covered, which is the hardest part for an agent to infer. But for a tool whose payload is a 22-variant operation union with no output schema, it says nothing about whether operations apply sequentially or atomically, or what the response contains besides the draft id.

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 50%, and the description adds no meaning for any of the four parameters, including the enormous 22-variant `operations` union and the bare `name` field. The only param-adjacent information is an implied draftId return value, which is not an input at all.

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?

States a specific verb and resource — 'prepare a validated edit without changing the saved project' — and immediately distinguishes this staged operation from the two siblings that consume its result (preview_render, draft_apply). An agent knows exactly what this is and what it is not without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit three-step lifecycle: stage here, render with preview_render using the returned draftId, then commit with draft_apply. This is the rare case where the when/when-not and the alternatives are all named in the description itself.

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