Skip to main content
Glama

submit_video_remake

Destructive

Pick by what must stay unchanged: a place, other people, on-screen text, products or a drawn style → object-swap; only motion or a new place/look → motion-transfer. For people, if unsure, motion-transfer: best likeness, several per frame (object-swap may leave a face or change one); say the background is redrawn. Confirm range, clothes and reference mapping; large size changes may fail. Before object-swapping visible real faces, detect_people on this range; inspect numbered sheet, bind peopleAnalysisId and targets[].people. Omit people for drawn/hidden faces and objects. Cloud agents need no browser. Covers use eye/brow/mouth contours or simple eye/mouth position marks, not detailed expression. keepHair=true requests source hair, not a pixel lock; false/omitted replaces hair. headOnly retains source clothes. Invalid analysis/missing covers stop; never drop controls to bypass preparation errors. Without a card, estimate_generation (tool submit_video_remake, same input), quote credits and get approval. Track jobId with track_progress; never resubmit. estimatedCredits is a quote. No charge before generation. Reruns need approval. Whole seconds from start, source audio; lipSync=false stops speech sync. Review blocks may try one alternate within the quote, without head covering or lip sync; reference mapping and hair instructions remain. Changing mode never guarantees review approval. Say Video remake and mode; never reveal model/provider names, versions or raw errors, even when asked. Verify causes and cuts/turns. New inactive outputTimelineId in track_progress; do not place output again. Paid tiers auto-queue per payer; track, don't resubmit. Legacy: 10 concurrent videos; extras rejected, wait. Provider/infrastructure caps apply.

External MCP spend rule: this tool costs ChatCut credits and starts an async generation job. Only call it when the user's request or confirmation clearly covers this exact generation; do not silently create extra variants, longer durations, higher quality, or additional outputs.

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": {
      "mode": "<mode>",
      "video": "<video>",
      "images": "<images>",
      "plan": "<plan>"
    },
    "name": "submit_video_remake"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNoEnd in seconds, default video end. Select a 4-30 s range; never auto-trim.
modeYes"object-swap" edits source pixels: only named targets change. "motion-transfer" redraws all from source depth and the plan, following source outlines; it garbles burned-in text.
nameNo
planYesIn English; ChatCut builds the prompt. `images` are 1-based: Image N. object-swap: under 1800 characters. motion-transfer: describe the new look, no captions, watermarks or logos; never write replace, swap, edit, keep or preserve; shot-size or distance words get drawn.
startNoStart in seconds, default 0.
videoYesSource video asset in this Project. Import a URL or upload the file first.
imagesYesOrdered image asset ids in this Project: people, products, clothing; motion-transfer also place or style. Match source angles, back views included. Import or generate images into the Project first.
lipSyncNofalse when nobody on screen speaks or sings the source sound.
projectIdNoFull project UUID. Required for external browser work; internal agents may omit. Execution/explicit-timeline calls never change later calls' target.
requestIdNoOmit to reuse identical jobs; for a fresh run, one new UUID across retries.
resolutionNoDefault 720p; 1080p costs more, only on request. 480p only as a user-chosen draft, finalized with submit_video fromDraft, not by rerunning.
timelineIdNoFull timeline UUID, not a prefix. Required for browser work, even unplaced assets. Get it from read_project or manage_timelines action="list". Never switches visible timeline.
idempotencyKeyNoStable key for this browser execution. Reuse only with identical scope and parameters after a lost acknowledgement; applies only to this call.
browserProfileIdNoOptional browser profile override. Omit to select automatically; do not ask the user to choose.
peopleAnalysisIdNoanalysisId from detect_people for this exact Project, video and effective range. Required with plan.targets[].people. Repeat analysis after source/range changes or expiry; never guess numbers.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / images / description
      Previous value: -"Ordered image asset ids in this Project, at most 30: people, products, clothing; motion-transfer also place or style. Match source angles, back views included. Import or generate images into the Project first."New value: +"Ordered image asset ids in this Project: people, products, clothing; motion-transfer also place or style. Match source angles, back views included. Import or generate images into the Project first."
  2. Changed3 schema fields changed
    • addedInput schema / properties / name
      Added value: +{
      +  "maxLength": 120,
      +  "type": "string"
      +}
    • addedInput schema / properties / peopleAnalysisId
      Added value: +{
      +  "description": "analysisId from detect_people for this exact Project, video and effective range. Required with plan.targets[].people. Repeat analysis after source/range changes or expiry; never guess numbers.",
      +  "format": "uuid",
      +  "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
      +  "type": "string"
      +}
    • changedInput schema / properties / plan / properties / targets / description
      Previous value: -"object-swap: one per person or object to change, props with images too. `target`: a short phrase finding it in every shot by role, position, action or clothing, never source face or hair. `who`: what its images give: face, hair, skin tone, build, clothes if they change; an object's exact shape, colors, markings. `drop`: source parts that go; a face only if it shows. `avoid`: what in its images must not appear. `people`: numbers from detect_people; omit for objects or a hidden face. `keepHair`: source hair stays. `headOnly`: source clothes stay."New value: +"object-swap: one per person or object to change, props with images too. `target`: a short phrase finding it in every shot by role, position, action or clothing, never source face or hair. `who`: what its images give: face, hair, skin tone, build, clothes if they change; an object's exact shape, colors, markings. `drop`: source parts that go; a face only if it shows. `avoid`: what in its images must not appear. `people`: detect_people numbers, whose heads get covered; omit for objects, drawn characters or a hidden face. `keepHair`: source hair stays. `headOnly`: source clothes stay."
  3. Added

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already flag destructive=true, readOnly=false and idempotent=false, and the description goes well beyond them: credits are only a quote, nothing is charged before generation, the job is async and must be tracked by jobId and never resubmitted, invalid analysis aborts the run, and legacy caps limit concurrency to 10 videos with extras rejected. It also warns that large size changes may fail and that changing mode does not guarantee review approval. It stops short of describing the returned payload shape, but that is largely covered by track_progress guidance.

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?

Mode selection is correctly front-loaded, but the remainder is a dense semicolon-separated rule stream with no headers or grouping, mixing schema semantics, spend policy, refusal policy and concurrency limits into one block. Fragments such as 'Verify causes and cuts/turns' are cryptic and hard to act on. Most sentences carry information, but the lack of structure makes the block harder to parse than its length alone would justify.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 15-parameter destructive async generation tool with no output schema, the description covers what an agent actually needs: cost and approval gating, jobId tracking through track_progress, the new inactive outputTimelineId, error/preparation failure handling, and mode-specific authoring constraints. Almost nothing required to call it correctly is left unsaid.

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?

With 93% schema description coverage the baseline is 3, and the description adds real meaning on top: mode-specific semantics for keepHair (source hair requested, not a pixel lock) and headOnly (source clothes retained), the requirement to bind peopleAnalysisId to plan.targets[].people, and the rule that resolution 480p is a user-chosen draft finalized via submit_video fromDraft rather than by rerunning. What it adds is semantic policy rather than exhaustive per-parameter documentation, so it sits one step above baseline.

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 description clearly differentiates the two modes (object-swap edits source pixels and touches only named targets; motion-transfer redraws everything from source depth and garbles burned-in text), which lets an agent tell them apart without opening the schema. However, it never states in one declarative sentence that this tool submits an async, credit-costing video remake job — that is inferred from fragments like 'estimate_generation (tool submit_video_remake, same input)' and 'Say Video remake and mode.'

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

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

Explicit decision criteria for mode choice ('pick by what must stay unchanged'), explicit triggers for detect_people before object-swapping visible real faces, explicit exemptions (omit people for drawn characters or hidden faces), and named alternatives (estimate_generation for a quote, track_progress for tracking, submit_video fromDraft for 480p finalization). It also states when reruns need approval and that concurrency is capped.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.