Skip to main content
Glama
aseprite-claude-connector

aseprite-claude-connector

clean_pixel_art

Merge tiny color patches into nearby colors within a tolerance and darken strong-edge shadows so noisy or pixelated art reads as drawn.

Instructions

Make pixelated or noisy art read as drawn: every patch of one colour smaller than min_region pixels merges into the colour around it, if that colour is close (tolerance, 0-1; standout specks like flowers stay), and firm_edges darkens the shadow side of strong edges with the art's own darker shade. No new colours. layer defaults to the active one; 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_pixel_art"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileNo
frameNo
layerNo
toleranceNo
all_framesNo
firm_edgesNo
min_regionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations carry only a title, so the description bears the full behavioral burden and does well: it discloses that no new colours are introduced, that the action is a single undo step, that it operates on the active layer by default, and that headless use requires passing file. It does not cover failure modes or what is returned, but the key destructive-scope facts are present.

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?

The effect is front-loaded in the first clause and every subsequent sentence adds operational facts rather than filler. The dense run-on phrasing with inline backticked parameter names is efficient, though slightly harder to scan than separate short clauses would be.

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 7-parameter mutation tool with no output schema and no meaningful annotations, the description covers scope, defaults, side effects, and the headless path. Remaining gaps are minor: it doesn't say what happens when the target layer or frame is missing, or what the call returns.

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 description coverage and 7 parameters, the description compensates strongly: it explains min_region as a pixel threshold, tolerance as 0-1 colour proximity, firm_edges as shadow-side darkening, layer defaulting to active, and file as the headless entry point. Only frame is not explicitly described beyond the 'one frame, or all_frames' phrasing.

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 states a specific transformation ('every patch of one colour smaller than min_region pixels merges into the colour around it') on a specific resource (pixelated/noisy art), plus a second concrete effect (firm_edges darkening). An agent can tell this is a targeted cleanup operation, though it never names or contrasts itself with nearby siblings like clean_lines or add_outline.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the opening framing ('make pixelated or noisy art read as drawn') and by the note that standout specks stay, which hints at when the tool is appropriate versus a blanket blur. However, there is no explicit when-to-use/when-not guidance and no alternative tool is named, so the agent must infer the boundary conditions.

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