Skip to main content
Glama
aseprite-claude-connector

aseprite-claude-connector

check_consistency

Read-only

Compare sprites within a character set to detect color drift and scale differences; reports near-duplicate and unique colors plus subject height for palette fixes.

Instructions

Compare sprites of one character or set: the open sprites (live; only picks them by filename or tag), or files. Reports colours so close they should be one (the drift you get from pixelating poses separately), the colours only one sprite uses, and how tall the subject stands on frame 1 of each, so differences in scale show. Close colours every sprite uses side by side are shading steps, not drift. Poses lying down or crouching are shorter by nature. Fix colours with match_palettes. Read-only.

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": "check_consistency"
  }
}

Input Schema

NameRequiredDescriptionDefault
onlyNo
filesNo
toleranceNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, so the 'Read-only' line is largely redundant. The description does add value by characterizing what the report contains and caveats for false positives, but it doesn't describe the output structure or how many findings are 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?

Purpose and source options are front-loaded, followed by interpretation guidance. Sentences are dense but each carries information; a stray double-space and backtick markup are minor noise.

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?

With no output schema and 0% schema coverage, the description does a fair job of explaining what the report surfaces, but omitting the tolerance parameter leaves an agent unable to tune sensitivity. For a three-parameter analysis tool this is an avoidable gap.

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 coverage is 0%, so the description must carry parameter meaning. It explains `only` (filename or tag) and `files` as alternative sources reasonably well, but never mentions `tolerance`, the key threshold controlling what counts as a close colour. That omission leaves a central knob undocumented.

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 opens with a specific verb and resource ('Compare sprites of one character or set') and enumerates what it reports: near-duplicate colours, colours unique to one sprite, and subject height on frame 1. It implicitly distinguishes itself from match_palettes, which it names as the fixer rather than the checker.

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 explains source selection (open sprites, `only` by filename/tag, or `files`) and gives interpretation rules that genuinely guide usage: close colours used side by side by every sprite are shading steps, and lying/crouching poses are naturally shorter. It also routes fixes to match_palettes. The only gap is no explicit 'when not to use' exclusion.

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