Skip to main content
Glama

Generate an animated sprite with ChatGPT

generate_sprite

Generates a sprite sheet from a character prompt and motion, then cuts and aligns frames locally into a transparent GIF, atlas, and manifest for animation use.

Instructions

Ask ChatGPT to draw poses in one sprite sheet; Backdraw cuts and aligns frames locally, saving a transparent GIF, atlas and manifest. Retries once in a new chat if count, empty-frame or identity checks fail. Returns a job_id; follow with job_status. For another motion of the same character, pass a frame from the previous GIF folder or a character PNG in reference_images.

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": {
      "prompt": "<prompt>",
      "motion": "<motion>"
    },
    "name": "generate_sprite"
  }
}

Input Schema

NameRequiredDescriptionDefault
sizeNo
viewNoside
framesNo
motionYes
promptYesCharacter description.
backgroundNotransparent
output_dirNo
wait_secondsNoReturn within this many seconds. The default 45 keeps each call under the 60-second tool limit some clients have. If the job has not finished by then, the result says STILL RUNNING or QUEUED: call job_status with its job_id again.
filename_hintNo
include_previewNo
reference_imagesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.3.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare openWorldHint=true and idempotentHint=false, but the description adds genuinely new behavior: local frame cutting/alignment, the three artifacts written to disk, and an automatic single retry in a new chat when frame-count, empty-frame or identity checks fail. The main omission is cost/latency expectations for a generation job and where files land relative to output_dir.

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?

Three dense sentences, front-loaded with what the tool produces, then failure handling, then the workflow handoff. Wording like "Backdraw cuts and aligns frames locally" earns its place by explaining the pipeline, though the reference_images sentence is slightly compressed.

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

Completeness3/5

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

The workflow loop (submit, get job_id, poll job_status, reuse a frame for the next motion) is covered, which is the core complexity for this async generator. However, with 11 parameters, no output schema, and no description of the call's return payload beyond a job_id, several inputs an agent must set remain unexplained.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 18% across 11 parameters, so the description needs to compensate and largely does not. Only reference_images is explained (reuse a prior frame or character PNG); size, view, frames, motion, background, output_dir, filename_hint and include_preview are left entirely to their enum names. wait_seconds happens to be well documented in the schema, but that is not the description's contribution.

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 names a specific action and artifact: ChatGPT draws poses into one sprite sheet, then frames are cut, aligned and saved as a transparent GIF, atlas and manifest. It also separates the async half of the operation ("Returns a job_id; follow with job_status"), which makes it distinguishable from siblings like generate_image and animate_sheet without opening any schema.

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?

It gives concrete follow-up guidance (call job_status with the job_id) and a clear continuation pattern ("For another motion of the same character, pass a frame from the previous GIF folder or a character PNG in reference_images"). It stops short of any when-not-to-use guidance relative to sibling tools such as animate_image or generate_image.

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