Skip to main content
Glama
Sign In
premiere-pro-mcp

premiere-pro-mcp

by matt-j-penny
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Detect Repeated Takes

detect_repeated_takes
Read-onlyIdempotent

Detect repeated sentence takes in a word timeline, group retakes, and plan which ranges to remove while keeping one take; returns keep/removal ranges and apply routes without editing Premiere.

Instructions

Detect repeated sentence takes (retakes) in a word timeline using token similarity within a time window, and plan removal of all but the kept take. Returns take groups, removal and keep ranges, and apply routes. Local-only; never changes Premiere.

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": {
      "word_timeline": "<word_timeline>"
    },
    "name": "detect_repeated_takes"
  }
}

Input Schema

NameRequiredDescriptionDefault
keepNoWhich take in each group to keep; defaults to last.
min_wordsNoMinimum tokens a sentence needs before it is compared; defaults to 4.
frame_rateNoTimebase used to snap ranges to whole frames; defaults to 30.
max_groupsNoMaximum take groups to return; defaults to 64.
handle_framesNoFrames of handle left inside each removal so cuts are not tight; defaults to 1.
word_timelineYesCaller-supplied word-timed transcript for one Premiere source item. Words must be ordered by start time and bound to the transcript revision returned by get_clip_transcript_uxp. Different labeled speakers may overlap; same-speaker words may not, even when another speaker is between them.
max_gap_secondsNoOnly sentences starting within this many seconds of an earlier candidate are compared; defaults to 20.
expected_cep_targetNoOptional reviewed CEP sequence/clip identity and exact tick ranges. Checked before every generated command; UXP refuses this CEP-only guard.
similarity_thresholdNoToken Jaccard/containment similarity needed to group two sentences; defaults to 0.8.
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.

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

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description still adds real value by saying the tool only plans removal and never touches Premiere, and that it emits apply routes rather than performing edits. It does not discuss costing, limits, or how grouping degrades on ambiguous repeats, so it is not fully transparent.

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?

Three short sentences, front-loaded with the core action and mechanism, then outputs, then the safety constraint. No filler and no repetition of the title.

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?

With an output schema covering take groups, keep/removal ranges, and apply routes, the description need not explain return values; it correctly points to them and adds the local-only scope. What is missing is how the results are meant to be consumed (which apply/preview tool routes them) and the required provenance of word_timeline, so an agent still has to infer the downstream step.

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

Parameters3/5

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

Schema description coverage is 100% and every parameter (keep, similarity_threshold, max_gap_seconds, handle_frames, frame_rate, expected_cep_target, etc.) is documented in the schema. The description only alludes loosely to 'token similarity within a time window' and 'the kept take', adding no defaults, interaction notes, or edge-case behavior beyond what the schema already says. Baseline 3 applies.

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?

States a specific verb and resource ('detect repeated sentence takes (retakes) in a word timeline') plus the mechanism (token similarity within a time window) and the output/next step (plan removal of all but the kept take). That clearly separates it from generic analysis tools, but it never names a sibling such as plan_filler_word_removal or analyze_dialogue_edit_candidates, so an agent must infer the boundary itself.

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?

'Local-only; never changes Premiere' implies this is a planning pass whose results feed a separate apply step, which nudges the agent toward the right workflow. However, there is no explicit when-to-use/when-not-use guidance, no stated prerequisite that word_timeline must come from get_clip_transcript_uxp, and no mention of alternatives or follow-up tools.

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