Skip to main content
Glama
aseprite-claude-connector

aseprite-claude-connector

make_seamless

Rebuilds a texture so its edges tile without visible seams by shifting the active layer and rebuilding the cross band from existing pixels, useful for ground, wall, or water tiles.

Instructions

Make a texture repeat with no visible edge, for ground, walls, or water tiles. The layer (the active one by default) fills the canvas: it is shifted by half so its old edges meet in the middle, and that cross, band pixels wide (an eighth of the size by default), is rebuilt from patch-sized pieces of the texture itself. Check it with look after expand_canvas or by exporting a few side by side. One undo step. Headless: pass file.

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": "make_seamless"
  }
}

Input Schema

NameRequiredDescriptionDefault
bandNo
fileNo
seedNo
frameNo
layerNo
patchNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4/5.0
Behavior4/5

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

With only a title annotation, the description carries the load well: it discloses that the active layer is modified by default, that the canvas is shifted by half, the default band width ('an eighth of the size') and patch size, that the operation costs exactly 'one undo step', and that headless invocation needs file. It stops short of saying what happens on a locked/missing layer, whether non-square canvases are handled, or what is returned.

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?

Front-loaded with purpose, then mechanism, then verification, then undo and headless notes — a sensible ordering with no filler sentences. The reST-style backticks and awkward line breaks add visual noise but no wasted content.

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?

For a six-parameter mutation tool with no annotations and no output schema, the description covers purpose, defaults, side effects, and undo well. It is still incomplete on return behavior (does it hand back the image, a path, or nothing?) and on the seed/frame parameters, which an agent cannot supply correctly from what is written.

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

Parameters3/5

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

Schema description coverage is 0%, so the description must compensate, and it does for four of six parameters: band (width of the rebuilt cross), patch (size of source pieces), layer (defaults to the active one), and file (headless mode). The seed and frame parameters get no explanation at all, and the stated band default ('an eighth of the size') conflicts in spirit with the schema's null default, leaving the agent to infer that null means computed.

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 and outcome ('make a texture repeat with no visible edge') plus the concrete use cases (ground, walls, water tiles). It also names the mechanism (half-shift, band rebuilt from patches) so the agent knows this is a tileability operation, distinct from sibling image tools like make_autotiles or make_normal_map.

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?

Gives clear context for when to reach for it (seamless tiling textures for ground/walls/water) and a concrete verification workflow ('check it with look after expand_canvas or by exporting a few side by side'). It also names the headless condition ('pass file'), but never states exclusions or what to use instead when the texture is already seamless.

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