Skip to main content
Glama
aseprite-claude-connector

aseprite-claude-connector

split_into_layers

Separate an image into independent layers by placing seed points on each distinct area; parts grow until sharp color changes so each can be edited or animated alone.

Instructions

Separate a picture into parts on their own layers, like armour and meadow, so each can be edited or animated alone. seeds are points on each part: [{"name": "armour", "x": 90, "y": 40}, {"name": "meadow", "x": 5, "y": 5}]. The first part named ends up on top. Each part grows from its seeds and stops where colours change sharply, so put a seed on every distinct area of a part (a part may have many seeds). If a part leaks into another, add seeds where it leaked and run it again. layer defaults to the active one, which is hidden afterwards unless hide_source is false. Check the result with look and layer=. One undo step. Headless: pass file.

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": {
      "seeds": "<seeds>"
    },
    "name": "split_into_layers"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileNo
frameNo
layerNo
seedsYes
hide_sourceNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations carry only a title, so the description must do the work, and it does: it discloses the mutation, that the source layer is hidden afterwards unless hide_source is false, that the operation costs one undo step, and that file is required in headless mode. It stops short of explaining what the new layers are named or what happens if seeds resolve to nothing.

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?

Dense but front-loaded: purpose and the seed concept come first, then failure recovery, defaults, verification, and headless handling. Nearly every clause conveys actionable information, with only a slight run-on feel in the seeds paragraph.

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 five-parameter destructive tool with no output schema and no meaningful annotations, the description supplies the seed model, the side effects, undo cost, and verification path. The unaddressed frame parameter and the absence of any note on returned layer names are the only real gaps.

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?

With 0% schema coverage the description must define every parameter itself, and it well explains seeds (structure, ordering semantics: first part named ends up on top), layer (defaults to active), hide_source, and file. The frame parameter is never mentioned, leaving one of five parameters undocumented in both schema and prose.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb and resource ("Separate a picture into parts on their own layers") plus a concrete example of armour and meadow. It is clear on its own, but never contrasts itself with the related split_sheet sibling, so an agent must infer the difference from names alone.

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 real procedural guidance: put a seed on every distinct area, re-run with extra seeds where a part leaked, and verify with look and layer=. What is missing is any explicit when-not-to-use condition or a named alternative for splitting sprite sheets versus a single picture.

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