Skip to main content
Glama
aseprite-claude-connector

aseprite-claude-connector

find_stray_pixels

Read-only

Detect accidental-looking stray, orphan, rare-color, and near-duplicate pixels in pixel art and return a color-coded preview for review.

Instructions

Find pixels and colors that look like accidents, and return a picture of them: the art in gray, with floating isolated pixels in red, orphan pixels (touching art but matching none of it) in yellow, and pixels of colors used rare times or fewer in magenta. Also lists near_duplicates: colors within near of a much commoner one. Dithering and highlights can be deliberate orphans, so treat this as a list to look over, not to erase. Defaults to the active frame, all visible layers. Read-only. 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": "find_stray_pixels"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileNo
nearNo
rareNo
frameNo
layerNo
max_sizeNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4.6/5.0
Behavior5/5

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

Beyond readOnlyHint=true, the description explains exactly what comes back — gray art with red isolated pixels, yellow orphans, magenta rare colors, plus a near_duplicates color list — and flags the false-positive risk from dithering and highlights. It also discloses the frame/layer defaults and that a file argument is required in headless mode, which the annotation block does not cover.

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?

Front-loaded with the purpose, then the output legend, then the interpretive caveat, then scope defaults and the headless note. No sentence is filler and no information is repeated from the schema or annotations.

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 analysis tool with no output schema the description covers return content, interpretation risk, and scope defaults well. The residual gap is `max_size` and whether near_duplicates arrives as text alongside the image; these are minor but real for an agent deciding how to consume the result.

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, the description carries the burden and largely succeeds: `rare` is defined as a usage-count threshold, `near` as color proximity to a much commoner color, `file` as the headless input, and frame/layer defaulting is explained. `max_size` is never mentioned and the distance metric behind `near` is left vague, so it is not fully complete.

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 resource ('Find pixels and colors that look like accidents') and immediately describes the deliverable — an annotated preview image with a color legend. This is clearly distinguishable from pixel-readers like get_pixels or look, which return raw data rather than a diagnosis overlay.

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 real usage framing: 'treat this as a list to look over, not to erase' warns against acting destructively on the results, and it states the default scope (active frame, all visible layers) plus the headless entry path. It stops short of naming an alternative tool or an explicit when-to-use trigger, so a 4 rather than a 5.

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