premiere-pro-mcp

Overview Schema Source Related Servers Discussions Admin

Roll Edit

roll_edit

Perform a verified roll edit at a clip's outgoing cut, moving visible edges and source in/out points while keeping linked audio/video in sync by default.

Instructions

Perform a verified roll edit at the outgoing cut of a clip using the public timeline DOM, moving both visible edges and their source in/out points and verifying all four. Linked audio/video partners get the same edit by default (include_linked); every clip is checked before any is changed. Requires readable finite media and ffprobe duration evidence for every edited source; refuses unknown duration, stills, and nonunit/reversed speed before mutation. Existing host Out padding below one sequence frame may be preserved or reduced, but never used to create additional padding.

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": {
      "node_id": "<node_id>",
      "offset_seconds": "<offset_seconds>"
    },
    "name": "roll_edit"
  }
}

Input Schema

Name	Required	Description
`node_id`	Yes	Node ID of the clip
`include_linked`	No	Also apply the edit to the clip's linked audio/video partners so picture and sound stay in sync (default: true).
`offset_seconds`	Yes	Offset in seconds (positive = roll right, negative = roll left)
`idempotency_key`	No	Optional 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_target`	No	Optional reviewed CEP sequence/clip identity and exact tick ranges. Checked before every generated command; UXP refuses this CEP-only guard.
`expected_project_path`	No	Optional 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

Name	Required	Description
`ok`	Yes	Whether the tool completed successfully.
`data`	No	Tool-specific result data when ok is true; on failure, diagnostic detail when the tool provides it.
`tool`	Yes	The registered MCP tool name.
`error`	No	Failure detail when ok is false.
`receipt`	No	Versioned common mutation receipt; success never implies rendered verification.
`idempotency`	No	Present 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.

First observedv1.30.0Nov 14, 2026

TDQS

A4.1/5.0

Behavior5/5

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

Annotations only declare a non-read-only, non-destructive, non-idempotent mutation; the description adds the substantive behavior an agent actually needs: all four edges are verified, linked partners follow include_linked by default, and every clip is validated before any is changed (all-or-nothing). It also discloses the subtle padding rule (existing Out padding under one sequence frame may be preserved or reduced, never used to create padding), which is exactly the kind of edge-case behavior annotations cannot convey.

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?

Front-loaded with the action and scope, then the verification/refusal rules. The middle section is a dense run-on list of refusals and one sentence restates the include_linked default already in the schema, but almost every clause carries real operational constraints.

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 six-parameter, nested-schema mutation with an output schema and annotations, the description covers atomicity, verification, preconditions, and the padding edge case well. Remaining gaps (idempotency/replay semantics, CEP-vs-UXP guard behavior) are thoroughly handled in the schema, so an agent can still call it correctly.

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%, so every parameter including idempotency_key and expected_cep_target is already fully documented, establishing a baseline of 3. The description only adds behavioral meaning for include_linked (which the schema already states as default true) and sign direction (also in the schema), so it contributes little parameter-level information beyond 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?

"Perform a verified roll edit at the outgoing cut of a clip" names a specific verb and resource and pins the operation to a single cut, with enough mechanical detail (both visible edges plus source in/out) that an informed agent can separate it from slip/slide. It never names slide_edit or slip_edit, so sibling differentiation rests on the reader's editorial knowledge rather than explicit routing.

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?

Clear preconditions and refusal conditions are given: readable finite media, ffprobe duration evidence, refusal of unknown duration, stills, and nonunit/reversed speed before mutation. What is missing is any when-to-use-this-vs-alternative guidance (e.g. roll vs slide vs slip), so the agent knows the requirements but not the selection rule.

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

Deploy Server