Skip to main content
Glama

Ludo AI Game Assets

by ai.ludo
OverviewDiscussionsAdmin

animate3DModel

Generate text-driven skeletal animations for an already-rigged 3D model. Pass the rigged GLB in model (URL or base64; the 3D asset file, not an AI model name) and a motion prompt (e.g. "walking", "swinging its axe"). The model must already have a skeleton - rig it first with rigModel if not. The job result is num_variants candidate animations (default 4), each a standalone animation-only GLB (skeleton + one clip, no mesh) in glb_url plus an mp4 preview_url, so you can pick the best one and fuse it with your model in a game engine or three.js. mode selects the representation - rot_trans (default, rotation plus translation per bone, most faithful) or rot_only (rotation only, easier to retarget onto another skeleton in an engine). Animation quality is hit-or-miss, which is why multiple candidates are returned. Credits are held once per call regardless of variant count and refunded if the job fails or is cancelled. Async generation job: returns {id, status} - poll getApiJob (job and credit contract: see the server instructions).

Credits: This endpoint consumes 0.2 credits per call.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
requestBodyYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / requestBody / properties / model / description
      Previous value: -"URL or base64-encoded already-rigged GLB to animate. Rig it first via the rig endpoint if it has no skeleton."New value: +"The already-rigged 3D asset to animate, as a URL or base64-encoded GLB file (not an AI model name). Rig it first with rigModel if it has no skeleton."
    • changedInput schema / properties / requestBody / properties / request_id / description
      Previous value: -"Optional client-provided identifier, unique per request. Re-sending the same request_id returns the existing job instead of generating again. Also usable with the results endpoint."New value: +"Optional client-provided identifier, unique per request. Re-sending the same request_id returns the existing job instead of generating again. Also usable as the request_id filter of listGenerations."
  2. Changed8 schema fields changed
    • removedInput schema / properties / requestBody / properties / augment_prompt / default
      Removed value: -true
    • changedInput schema / properties / requestBody / properties / augment_prompt / description
      Previous value: -"Rewrite the prompt into a detailed motion caption with an LLM (recommended)."New value: +"Rewrite the prompt into a detailed motion caption with an LLM (recommended). Default: true."
    • removedInput schema / properties / requestBody / properties / loop / default
      Removed value: -true
    • changedInput schema / properties / requestBody / properties / loop / description
      Previous value: -"Return to the initial pose: each clip plays forward then mirrors back to the rest pose for a seamless loop. Best for one-way motions (crouch, punch, wave); reads oddly for cyclic gaits like walking."New value: +"Return to the initial pose: each clip plays forward then mirrors back to the rest pose for a seamless loop. Best for one-way motions (crouch, punch, wave); reads oddly for cyclic gaits like walking. Default: true."
    • removedInput schema / properties / requestBody / properties / mode / default
      Removed value: -"rot_trans"
    • changedInput schema / properties / requestBody / properties / mode / description
      Previous value: -"Animation representation: rot_trans (per-bone rotation+translation, most faithful) or rot_only (rotation + root translation only, for retargeting)."New value: +"Animation representation: rot_trans (per-bone rotation+translation, most faithful) or rot_only (rotation + root translation only, for retargeting). Default: \"rot_trans\"."
    • removedInput schema / properties / requestBody / properties / num_variants / default
      Removed value: -4
    • changedInput schema / properties / requestBody / properties / num_variants / description
      Previous value: -"Number of candidate animations to generate; each returned as a standalone animation-only GLB with an mp4 preview."New value: +"Number of candidate animations to generate; each returned as a standalone animation-only GLB with an mp4 preview. Default: 4."
  3. Changed1 schema field changed
    • changedInput schema / properties / requestBody / properties / request_id / description
      Previous value: -"Optional client-provided id to retrieve the result later."New value: +"Optional client-provided identifier, unique per request. Re-sending the same request_id returns the existing job instead of generating again. Also usable with the results endpoint."
  4. Changed1 schema field changed
    • changedInput schema / properties / requestBody / properties / model / example
      Previous value: -"<url> OR data:image/png;base64,..."New value: +"<url> OR data:model/gltf-binary;base64,..."
  5. Added

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations available, the description carries the full behavioral burden, and it delivers: it discloses that this is an async generation job returning {id, status}, that credits are held once and refunded on failure/cancellation, that quality is hit-or-miss, and that results are standalone animation-only GLBs with mp4 previews. It also explains the mode trade-off and output shape, which is far beyond what structured annotations would provide.

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?

The description is dense but long, packing many necessary operational details into a few sentences. It is front-loaded with the core purpose and then moves through input, output, mode, quality, and credits. It is arguably slightly verbose, but each sentence earns its place given the asynchronous, credit-bearing, multi-variant behavior.

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 complex tool with no output schema, the description explains the job lifecycle, the poll target, the output artifact shape, and the credit contract. It even warns about unreliable animation quality and points to server instructions for the job/credit contract. Nothing critical for selecting and invoking this tool is missing, though exact response fields could always be more exhaustive.

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?

The top-level parameter has no schema description, so the description adds essential meaning: it clarifies `model` as a URL or base64 GLB, clarifies `mode` as rot_trans vs rot_only with retargeting implications, and explains `num_variants` as producing one candidate per variant. It does not cover `loop`, `augment_prompt`, or `request_id`, though those do have their own nested schema descriptions.

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?

The description opens with a specific verb and resource: 'Generate text-driven skeletal animations for an already-rigged 3D model.' It also differentiates from siblings by naming rigModel for the rigging prerequisite and clarifying that `model` is a 3D asset file, not an AI model name. The purpose is unmistakable and distinct from animate3DModelPreset, animateSprite, and transferMotion.

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?

The description states when to use the tool: for an already-rigged model with a motion prompt, and explicitly says to rig first with rigModel if there is no skeleton. It also clarifies the model input format with an exclusion ('not an AI model name'). It does not explicitly contrast this with animate3DModelPreset or listAnimationPresets, so it stops short of a full when/when-not matrix.

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

All Ludo AI Game Assets toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources