Skip to main content
Glama

Execute canonical editor action

execute_action
Destructive

Run any canonical editor action or inspection tool directly on a project scene, and bootstrap a new project by passing a video URL or assets on the first call.

Instructions

Execute any single canonical editor action (all 189+ actions) or read/inspection tool (list_layers, inspect_layer, query_transcript, list_sources, search_shots, shot_timeline, read_source_transcript, measure_audio, measure_picture, measure_color) directly on a project scene without autonomous_edit. Pass video_url or assets on the first call to bootstrap a new project.

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": {
      "action": "<action>"
    },
    "name": "execute_action"
  }
}

Input Schema

NameRequiredDescriptionDefault
sceneNoOptional inline scene.
actionYesCanonical action name (e.g. REGISTER_REMOTE_ASSET, SET_SOURCE_RANGE, TRIM_LAYER, REMOVE_SILENCES, CONFIGURE_CANVAS, VERTICAL_REFRAME, COLOR_GRADE, APPLY_VFX, TITLE_CARD, PLAN_MOTION_GRAPHICS, GENERATE_CAPTIONS, STYLE_CAPTIONS, CLEAN_AUDIO, GENERATE_VOICEOVER, GENERATE_MUSIC, ADD_SFX, AUTO_DUCK, RENDER_PREVIEW, EXPORT_VIDEO) or read tool name (e.g. list_layers, query_transcript).
assetsNoOptional media assets to seed a new project.
video_urlNoOptional source video URL to seed a new project.
project_idNoProject id for state persistence across calls.
action_paramsNoParameters for the canonical action (see get_action_schema).
include_sceneNoIf true, include the full raw scene JSON in the response (omitted by default in favor of liveLayers).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.7.1

TDQS

A4/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false and openWorldHint=true, so the safety profile is covered. The description adds real context by noting that read-only inspection tools also live behind this write-capable entry point and by explaining the first-call project bootstrap. It does not say what side effects an action can have, whether actions are reversible, or how failures surface, which matters for a destructive 189-action dispatcher.

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?

Two sentences, front-loaded with the capability and its scope, with the sibling exclusion stated immediately. The parenthetical enumeration of ten read tools is long but earns its place by telling the agent it need not look for a separate inspection tool.

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 destructive, open-world dispatcher with seven parameters and no output schema, the definition covers the core routing and bootstrap story. It leaves gaps around the response contract (only the schema's include_scene hint mentions liveLayers), how action_params is validated, and what state project_id persistence implies across calls.

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 100%, so the schema carries the parameter definitions and the baseline would be 3. The description goes beyond it by specifying the sequencing semantics of video_url and assets ('on the first call to bootstrap a new project'), which the schema only describes as 'optional ... to seed a new project' without the ordering constraint.

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?

The description states a specific verb ('Execute') and a precisely bounded resource ('any single canonical editor action (all 189+ actions)'), then extends the scope to named read/inspection tools. It explicitly contrasts with the autonomous_edit sibling, so an agent can route between them 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 Guidelines4/5

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

It gives clear routing guidance: use this to run a single action or read tool 'directly on a project scene without autonomous_edit', and it names the bootstrap path (pass video_url or assets on the first call). What is missing is an explicit statement about when to prefer execute_batch or queue_edit over this tool; the word 'single' implies but does not state the boundary.

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