Skip to main content
Glama

Scene Edit Detection

scene_edit_detection

Detect scene edits in selected Premiere clips, then create segmentation markers or razor cuts at each detected boundary. Use sensitivity controls to tune detection for your footage.

Instructions

Perform Premiere's scene edit detection on the selected clips in the active sequence (it analyses the footage and can take minutes on long clips). CreateMarkers (default) puts Segmentation markers on the selected clips' source project items (shared by every sequence that uses them), removes duplicates this run created (markers that were already there are never deleted), and reports each detected cut in source and timeline seconds; it is verified only when at least one new marker was added. ApplyCuts razors the selected clips and verifies the clip count grew. EXPERIMENTAL QE: CreateMarkers records an observed marker boundary for guarded Undo/Redo; crossing it is refused by default, and unreadable history records unknown protection. This boundary does not verify native marker reversal.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "scene_edit_detection"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionNoCreate markers (default) or apply cuts to the selected clips
sensitivityNoScene-detection sensitivity (default: MediumSensitivity)
idempotency_keyNoOptional client-chosen key (1-128 chars of A-Z a-z 0-9 . _ : -) for this intended edit. Pass a fresh key per edit and reuse it only when retrying that same edit, for example after a client-side timeout. A repeat with the same tool, key and arguments is not run again: while the first call is running it fails with IDEMPOTENCY_IN_PROGRESS (poll get_last_operations); after it finished it returns the original outcome marked replayed. A definite failure with nothing applied (receipt outcome not_applied) may be retried with the same key. Reusing a key with different arguments fails with IDEMPOTENCY_KEY_REUSED. Scoped to this MCP session (the stdio server process, or the HTTP server process when Streamable HTTP is stateless per request) and held in memory only (200 keys, 1 hour); it does not survive a restart or reconnect. Read-only invocations are never deduplicated.
expected_cep_targetNoOptional reviewed CEP sequence/clip identity and exact tick ranges. Checked before every generated command; UXP refuses this CEP-only guard.
expected_project_pathNoOptional absolute saved-project path. Every generated CEP command refuses before its body when the active project differs or is unsaved. UXP commands refuse this CEP-only guard; local-only tools do not inspect Premiere. Omit to keep existing behavior.
apply_cuts_to_linked_audioNoWhen applying cuts, also cut linked audio (default: false)

Output Schema

NameRequiredDescriptionDefault
okYesWhether the tool completed successfully.
dataNoTool-specific result data when ok is true; on failure, diagnostic detail when the tool provides it.
toolYesThe registered MCP tool name.
errorNoFailure detail when ok is false.
receiptNoVersioned common mutation receipt; success never implies rendered verification.
idempotencyNoPresent when idempotency_key deduplicated this call: replayed is true when the original outcome was returned instead of running again.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.30.0

TDQS

A4.4/5.0
Behavior5/5

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

With annotations only declaring readOnlyHint=false and destructiveHint=false, the description carries the important side effects: markers land on the selected clips' source project items and therefore affect every sequence using them, duplicates the run created are removed but pre-existing markers are never deleted, and verification is tied to at least one new marker or grown clip count. It also discloses runtime (minutes on long clips) and the experimental Undo/Redo boundary that refuses crossed boundaries by default and reports 'unknown protection' for unreadable history.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded and every sentence is substantive, but the prose is long run-on text with stacked parentheticals and an 'EXPERIMENTAL QE:' block that is hard to parse on a first read. The content mostly earns its place, yet the structure could be broken into scannable clauses without losing information.

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 mutating, nested-schema, output-schema-bearing tool, the description covers the side effects, verification semantics, runtime, and undo-guard behavior an agent needs before calling. It omits the safety guards exposed in the schema (idempotency_key, expected_cep_target, expected_project_path) and the linked-audio flag, though the 100% schema coverage partly compensates.

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 baseline is 3, but the description adds real meaning to the 'action' parameter by spelling out the divergent consequences of each enum value and its verification rule. It says nothing about sensitivity, apply_cuts_to_linked_audio, idempotency_key, or the expected-identity guards, so it does not fully supplant the schema.

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 opens with a specific verb and resource: 'Perform Premiere's scene edit detection on the selected clips in the active sequence', and it disambiguates the two operating modes (CreateMarkers vs ApplyCuts) with concrete outcomes for each. An agent can distinguish this tool from siblings like detect_scene_edits without opening the 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 clearly frames the operating context (a selection exists in the active sequence, footage may be long) and explains what each action produces, which is the main selection decision. It never names an alternative sibling or states when-not to use this tool versus detect_scene_edits/plan_scene_segments, so it stops short of full routing guidance.

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