Skip to main content
Glama
clipugc

clipugc

Official
by clipugc
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Create a motion-control clip

create_motion_clip

Animate a character look or your own photo by copying the motion of a driver video to generate a short clip. Upload the driver, poll the video status, then download the result.

Instructions

Animate a character look (or your own photo) by copying the motion of a driver video. Same as clipugc videos motion. Two engines: kling (default, 3 credits per second of driver video, reads the prompt) or wan (2 credits per second, keeps the look's own background, ignores the prompt, resolution 480p, 580p or 720p). Rounded up, capped at 30 seconds (confirm with get_credits). The driver must be mp4/mov, at most 50 MB and 30 seconds; it is uploaded first. Provide exactly one of image or photo. Returns the clip id and status. Generation runs in the background. Poll get_video with {"id": , "kind": "clip"} every 5 to 10 seconds until status is "completed" or "failed", then call download_video.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
imageNoId of a generated character look (same as --image).
photoNoLocal path to your own photo, png/jpg/jpeg/webp; uploaded first (same as --photo).
driverYesLocal path of the driver video, mp4/mov, max 50 MB and 30s (same as --driver).
engineNokling (default) or wan, the cheaper engine (same as --engine).
promptNoWhat the character does, max 1500 chars (same as --prompt).
keep_soundNoKeep the driver video's original sound (same as --keep-sound).
resolutionNowan only: 480p, 580p or 720p, default 720p (same as --resolution).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.4.0
    • addedInput schema / properties / engine
      Added value: +{
+  "description": "kling (default) or wan, the cheaper engine (same as --engine).",
+  "enum": [
+    "kling",
+    "wan"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / resolution
      Added value: +{
+  "description": "wan only: 480p, 580p or 720p, default 720p (same as --resolution).",
+  "enum": [
+    "480p",
+    "580p",
+    "720p"
+  ],
+  "type": "string"
+}
  2. First observedv1.0.0

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the annotations (readOnly=false, openWorld=true, destructive=false) by disclosing credit pricing per engine, the 30s cap with a get_credits confirmation step, driver file constraints (mp4/mov, 50 MB, 30s, uploaded first), background/async execution, and a concrete polling interval and terminal statuses.

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?

Purpose is front-loaded in the first sentence and the remaining sentences each carry operational payload (costs, limits, workflow). It is dense and slightly long, and the 'Same as `clipugc videos motion`' CLI mapping is marginal, but there is no filler.

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?

With no output schema, the description still states the return shape ('clip id and status') and the complete follow-up path via get_video and download_video. For a 7-parameter async generation tool, nothing an agent needs to invoke and follow through is missing.

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 baseline is 3, but the description adds real value the schema lacks: the image/photo mutual-exclusion rule ('exactly one of'), that prompt is only read by kling, that resolution is wan-only with a 720p default, and the credit cost differences between engines.

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?

States a specific verb+resource ('Animate a character look ... by copying the motion of a driver video') and distinguishes itself from sibling clip creators like create_clip and create_scene_replace_clip by naming the motion-copy mechanism and the two supported source types.

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?

Gives explicit operating conditions: exactly one of image or photo, engine selection tradeoffs (kling reads prompt, wan keeps background/ignores prompt), and a full post-call workflow (poll get_video, then download_video). It does not explicitly contrast when to choose this tool over the other clip-creation siblings, which keeps it below a 5.

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