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

agent-video-engine

by ferdy252
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

edit_apply

Apply a validated batch of video timeline edits as one revision, including clip, caption, overlay, audio, and transition changes, while leaving the project unchanged if the batch is invalid or stale.

Instructions

Apply a complete validated batch as one revision. Timeline controls: set_clips, insert_clip, replace_clip, insert_gap, set_gap, split_clip, remove_clip, trim_clip, reorder_clips, delete_source_range, delete_words. Set an incoming crossfade/dip/wipe with set_transition (overlaps existing retained ranges and shortens output). set_clip_visual controls crop, focus, fit, position and timed motion keyframes. set_clip_audio controls independent source bounds/offset, gain, role, fades and volume envelope; patch:null restores linked sound. set_audio controls voice/music/effects gains, optional music ducking, voice noise reduction and automatic loudness. upsert_overlay adds media or reusable title/lower_third/callout text. set_caption_cues edits wording, line breaks and fixed output timing; cues:null returns to source-timed captions. Also supports remove_overlay, set_captions, set_settings, set_custom, set_asset_color and set_clip_color. Use draft_stage for a proposal preview. Invalid or stale batches leave the project unchanged. Originals are preserved.

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": "edit_apply"
  }
}

Input Schema

NameRequiredDescriptionDefault
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

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnly=false, destructive=false and openWorld=false, so the bar is lower, and the description still adds real behavior: stale or invalid batches leave the project unchanged, originals are preserved, and transitions overlap retained ranges and shorten output. That explains why clip/media removal operations do not make (and cannot revert) destructive edits to source media. It does not say what the tool returns or how the new revision is reported, which is the remaining gap.

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?

The core purpose is front-loaded, and every sentence maps to a distinct operation family, so little is padded despite the length. The drawback is that a 20-plus-item enumeration is delivered as one unbroken paragraph, which makes scanning for a specific operation harder than a compact list would.

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 a large multi-variant mutation tool with a deep nested schema and no output schema, the description covers atomicity, the null-reset conventions, transition side effects, and a preview alternative. The main omissions are the return value/revision reporting and an explicit statement of the draft_apply versus edit_apply distinction.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 67%, with projectDir and expectedRevision documented in-schema, so the burden falls on explaining the operations array. The description does this well, attaching meaning to operation variants that the schema only types: patch:null restores linked sound, cues:null returns to source-timed captions, set_transition shortens output. Individual field semantics inside each operation (crop, motion keyframes, envelope) are left to the schema.

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 opening sentence states a specific verb and resource: applying a complete validated batch as one revision. The enumeration of operation types (set_clips, split_clip, upsert_overlay, set_audio, etc.) makes the tool's remit unmistakable. It stops short of a clean one-line contrast against the closest sibling draft_apply, which keeps it from a 5.

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?

Usage guidance is limited to a single routing hint: 'Use draft_stage for a proposal preview.' That is useful, but the obvious alternative in the sibling list, draft_apply, is never named or contrasted, nor are prerequisites such as needing a prior project_inspect to obtain expectedRevision. The agent must infer the workflow.

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