Skip to main content
Glama

Animate a sprite sheet locally (no ChatGPT)

animate_sheet

Splits a local sprite-sheet PNG into aligned animation frames, a transparent looping GIF, atlas, manifest, frame PNGs, and contact preview in a new folder, leaving the source image unchanged.

Instructions

Split a local sprite sheet PNG with all poses in one image into aligned frames and a transparent looping GIF, atlas PNG, manifest, frame PNGs and contact preview in a new sibling folder. No ChatGPT or Chrome; takes seconds. The source PNG is never changed. Frames share a ground line and horizontal center of mass; jump adds an upward arc. Report quality warnings to the user. For light motion from one image, use animate_image.

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": {
      "image_path": "<image_path>",
      "motion": "<motion>"
    },
    "name": "animate_sheet"
  }
}

Input Schema

NameRequiredDescriptionDefault
fpsNoUniform frame timing, overriding the motion profile. Cannot be combined with durations_ms.
rowsNoProvide with columns.
sizeNoGIF long-edge limit; default source scale. Whole-number nearest-neighbor enlargement or premultiplied-alpha area downscaling. Atlas and PNG frames stay at source scale.
framesNoExpected frame count; must agree with columns times rows when both are given. Omit all for automatic extraction.
motionYes
columnsNoProvide with rows; 2-64 cells in total.
air_framesNoJump only: inclusive [first, last] airborne frames, 1-based.
backgroundNoAlways saves a transparent GIF; white also saves a white GIF and lists that one in the gallery.transparent
image_pathYesLocal PNG; relative paths are resolved from the server's current folder.
jump_heightNoJump only: arc peak in source pixels; default half the median frame height.
durations_msNoOne duration per found frame; overrides the motion profile.
include_previewNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.3.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations declare a non-read-only, non-destructive, non-idempotent, closed-world operation, and the description adds genuinely non-structured behavior: the source PNG is never modified, outputs land in a new sibling folder, frames are ground-line aligned and horizontally center-of-mass aligned, jump arcs upward, and quality warnings must be surfaced to the user. It does not say what happens when the target folder already exists (overwrite vs. versioning) or whether runs are repeatable, which is the remaining gap for a tool that writes files.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and outputs come first, constraints and the source-immutability guarantee follow, and the sibling redirect is last, which is the correct routing order. Every sentence carries distinct information (outputs, environment, immutability, alignment, warnings, alternative) with no restatement of the title.

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?

For a 12-parameter local file-producing tool with no output schema, the description covers what is produced, where it goes, what is left untouched, and that warnings are part of the result. The gap is operational edge cases (existing output folder, failure mode for a malformed sheet), which the 83%-covered schema does not address either.

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 description coverage is already 83%, so the schema carries most parameter meaning. The description adds semantics the schema does not state: motion profiles drive the timing and jump behavior, jump introduces an upward arc tied to the jump parameters, and alignment guarantees apply across found frames. It does not clarify conflicts between fps and durations_ms or the meaning of the custom motion enum value beyond what the schema says.

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 (split) plus the input resource (a local sprite sheet PNG holding all poses) and enumerates the concrete artifacts produced: aligned frames, transparent looping GIF, atlas PNG, manifest, frame PNGs and a contact preview. It also names the sibling it is not (animate_image) and its scope condition ('light motion from one image'), so an agent can separate the two without reading either 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?

The closing sentence explicitly routes the agent: multi-pose sheet here, single-image light motion to animate_image. It also sets expectations that no ChatGPT/Chrome is involved and runtime is seconds. What is missing is guidance on when-not-to-use beyond that single alternative (e.g. what happens if the sheet already exists as a job, or how to choose between explicit frames/columns/rows and automatic extraction), so it stops short of a full when/when-not map.

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