Skip to main content
Glama
aseprite-claude-connector

aseprite-claude-connector

clean_lines

Turns rough sketched strokes into clean pixel-art lines by thinning them to one pixel and removing doubled corner pixels, optionally clearing isolated specks while preserving colors.

Instructions

Turn rough sketched strokes into clean pixel-art lines: thin brings thick strokes down to one pixel, and the doubled corner pixels freehand lines leave are removed, as Aseprite's pixel-perfect brush would have drawn them. specks also clears pixels with no neighbour. Kept pixels keep their colour. Use it on a line-art layer over transparency (layer, the active one by default); one frame, or all_frames. 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": "clean_lines"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileNo
thinNo
frameNo
layerNo
specksNo
all_framesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A3.8/5.0
Behavior3/5

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

Annotations carry only a title, so the description does the disclosure work: it states that kept pixels retain their colour, that the run is a single undo step, and that it targets the active layer by default. It does not say whether the operation can be re-run idempotently, how many pixels it touches, or what it returns, leaving meaningful behavioral gaps.

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 the core transformation, then parameter behavior, then the layer/frame scope and headless note; backticked parameter names tie claims to inputs. Dense but nearly every clause conveys information; the sentence about thick strokes and corner pixels is slightly long-winded.

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 six-parameter mutation tool with no annotation hints and no output schema, the description covers scope, defaults, side effects (one undo step) and headless behavior adequately. It omits any indication of what the call reports back on success or how it signals a non-line-art layer.

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 coverage is 0%, so the description must compensate and largely does: ``thin`` vs ``specks`` are defined by their pixel effects, ``layer`` defaults to active, ``all_frames`` vs a single frame is explained, and ``file`` is tied to headless use. The ``frame`` parameter's exact semantics (which frame is selected when null) remain only loosely implied.

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?

States a concrete transformation ("turn rough sketched strokes into clean pixel-art lines") and names the two effects it controls, so the resource and action are unambiguous. It does not differentiate itself from the sibling clean_pixel_art, which an agent could plausibly confuse with this tool.

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 applicability context: use it on a line-art layer over transparency, on one frame or all_frames, and pass ``file`` when headless. It stops short of explicit when-not-to-use guidance or naming an alternative tool for non-line-art cleanup.

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