Skip to main content
Glama

Generate an AI motion clip

generate_motion_clip
Idempotent

Turn a text-to-video prompt into ONE AI motion clip (Seedance 2.0 Mini). The prompt is sent EXACTLY as written: no script is written, no still images are made, no voice is added, nothing is rewritten or shortened. USE THIS TOOL when the user pastes or asks for a cinematic / video-model prompt (camera moves, lens, lighting, a scene description, "9:16 vertical", "slow dolly-in", the kind ChatGPT or Claude writes for Seedance, Sora or Veo). For a narrated story or facts video use create_video. The clip is silent (no audio, no lip-sync, no talking), 4-12 seconds (default 5), 480p. Price: 4 s = 92 credits, 5 s = 115, 12 s = 276; call quote_motion_clip first and tell the user the price before creating. These are the standard prices. A lower price applies for the credits bought in the last 31 days (an active paid plan period or a credit pack): the standard clip then costs 10 credits per second (5 s = 50). quote_motion_clip returns the exact price for THIS account. The credits are held when the clip is accepted and returned in full if no clip comes back. The only text added to the prompt is a short server suffix ("No spoken dialogue, no lip-sync, no talking to camera, no watermark."); the answer echoes promptSent and the seed so the user can see and repeat exactly what was made. Not accepted (CONTENT_POLICY, nothing charged): real or famous people, minors, sexual content, protected characters or brands, deepfakes and lip-sync. A first-frame photo is not supported. Optional templateId: one of the 26 ready clip templates from list_motion_templates; its prompt, seconds and aspect ratio are used. If you also pass prompt, the prompt wins and the template is ignored. An unknown templateId is refused (INVALID_INPUT, nothing charged). Any account with enough credits can use it: there is no plan or trial limit, too few credits is the only account refusal (INSUFFICIENT_CREDITS, nothing charged). At most 2 clips run at once; a daily capacity limit applies (DAILY_CAP_REACHED). Rendering is asynchronous: poll get_video every 20 seconds until COMPLETED (videoUrl is an MP4) or FAILED (errorCode, creditsRefunded). There are no webhooks. Pass idempotencyKey so a retry never charges twice. Requires the "video:create" scope. Optional tier: "seedance-2.5-480p" (Seedance 2.5 480p (with sound), 4-30 s, 68 credits per second: 5 s = 340, 15 s = 1020; 30 per second at the low price); "seedance-2.5-720p" (Seedance 2.5 720p (with sound), 4-30 s, 152 credits per second: 5 s = 760, 15 s = 2280; 66 per second at the low price); "wan-3.0-480p" (Wan 3.0 480p (with sound), 2-30 s, 33 credits per second: 5 s = 165, 15 s = 495; 15 per second at the low price); "wan-3.0-720p" (Wan 3.0 720p (with sound), 2-30 s, 66 credits per second: 5 s = 330, 15 s = 990; 29 per second at the low price); "wan-3.0-1080p" (Wan 3.0 1080p (with sound), 2-30 s, 131 credits per second: 5 s = 655, 15 s = 1965; 57 per second at the low price). A tier with sound returns the clip WITH an AI-generated sound track (speech, ambience) and the "no spoken dialogue" suffix is not added. Lip-sync, face swaps and talking avatars (a person talking to the camera) stay refused on every tier, with or without sound. A clip on an optional tier can take up to 30 minutes: keep polling, the credits stay held while it is being made. Without tier the clip is the standard silent one described above.

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": "generate_motion_clip"
  }
}

Input Schema

NameRequiredDescriptionDefault
seedNoOptional. The answer always returns the seed used; pass it again to ask for a similar take (the provider treats it as best effort).
tierNoOptional. A higher-quality model with sound: seedance-2.5-480p = Seedance 2.5 480p (with sound); seedance-2.5-720p = Seedance 2.5 720p (with sound); wan-3.0-480p = Wan 3.0 480p (with sound); wan-3.0-720p = Wan 3.0 720p (with sound); wan-3.0-1080p = Wan 3.0 1080p (with sound). Omit it (or pass seedance-2.0-mini-480p) for the standard silent clip. A tier with sound costs more per second: quote it first.
promptNoThe video prompt, exactly as the user wrote or pasted it (8-2000 characters). Do not summarise, translate or "improve" it: it is sent to the video model unchanged. Required unless templateId is given.
durationNoClip length in whole seconds (default 5). Up to 12 without tier; up to 30 with an optional tier. From 4 without tier; from 2 on a tier that makes shorter clips.
templateIdNoOptional. The id of a motion clip template (list_motion_templates): its ready-made prompt is sent as written. Ignored when prompt is also given.
aspect_ratioNoFrame shape (default 9:16, vertical).
idempotencyKeyNoRetry-safe: a repeat with the same key returns the first answer (replayed: true) and charges nothing.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / duration / description
      Previous value: -"Clip length in whole seconds (default 5). Trial accounts: at most 5. Up to 12 without tier; up to 30 with an optional tier. From 4 without tier; from 2 on a tier that makes shorter clips."New value: +"Clip length in whole seconds (default 5). Up to 12 without tier; up to 30 with an optional tier. From 4 without tier; from 2 on a tier that makes shorter clips."
  2. Added

TDQS

A4.4/5.0
Behavior4/5

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

Goes far past the annotations: silent vs. sound tiers, 4-12 s / 480p defaults, per-second pricing and credit hold/refund semantics, content-policy refusals that cost nothing, capacity limits (2 concurrent, DAILY_CAP_REACHED), the exact server suffix appended to the prompt, the required "video:create" scope, and the absence of webhooks. The only gap is that it does not discuss cost of the quote call or failure modes at the HTTP/transport level, which is minor given how much behavior is already disclosed.

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?

Front-loads purpose and when-to-use well, but the body is roughly 450 words and repeats itself — standard prices are stated, then re-stated per tier alongside the low-price figures, and the "no spoken dialogue" suffix rule appears twice. A complex paid tool justifies length, yet the tier enumeration could be compressed by pointing at quote_motion_clip rather than inlining six pricing tables.

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 no output schema, the description carries the return contract itself (promptSent and seed echoed, videoUrl MP4, errorCode, creditsRefunded) and explains the asynchronous lifecycle: poll get_video every 20 seconds, no webhooks, up to 30 minutes on premium tiers while credits stay held. That is complete enough for a 7-parameter mutating tool; only the precise shape of INVALID_INPUT / DAILY_CAP_REACHED payloads is left implicit.

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 schema already documents all 7 parameters, but the description still adds real meaning: per-tier credits-per-second pricing and worked examples, the precedence rule that a supplied prompt overrides templateId, and the retry/replay guarantee behind idempotencyKey. Some content (tier names, duration ranges, seed behavior) is duplicated rather than additive, keeping it just below a 5.

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 precise verb and artifact ("Turn a text-to-video prompt into ONE AI motion clip") and immediately scopes what it is not (no script, no stills, no voice). It names the sibling to use instead for narrated content (create_video), so an agent can separate it from the surrounding 33 tools without opening a schema.

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?

Gives an explicit trigger ("USE THIS TOOL when the user pastes or asks for a cinematic / video-model prompt" with example cues like "slow dolly-in", "9:16 vertical") plus a named alternative for the off-case (create_video for narrated story/facts). It also prescribes the required pre-step: call quote_motion_clip first and tell the user the price.

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.

Resources