Skip to main content
Glama
aseprite-claude-connector

aseprite-claude-connector

pack_atlas

Packs several sprites and every frame into one texture, then writes a JSON map in Aseprite's sprite-sheet hash layout so identical frames share pixels.

Instructions

Pack several sprites into one texture, with every frame of each, plus a JSON map in the hash layout of Aseprite's sprite-sheet export. Frames that repeat exactly share pixels. sprites are files on disk or, live, the file names of open sprites; unsaved sprites can't be named. The JSON goes beside the PNG unless out_json says otherwise, and frames are keyed <sprite> <index>.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "sprites": "<sprites>",
      "out_png": "<out_png>"
    },
    "name": "pack_atlas"
  }
}

Input Schema

NameRequiredDescriptionDefault
out_pngYes
paddingNo
spritesYes
out_jsonNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already establish openWorldHint=true and non-destructive behavior, so the bar is lower. The description does add real behavior: identical frames share pixels (deduplication), the JSON lands beside the PNG unless out_json overrides it, and frame keys follow '<sprite> <index>'. It still says nothing about return values, overwrite behavior if targets exist, or failure modes when a named sprite is unsaved.

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 core action and output artifacts are front-loaded in the first sentence, with constraints following in descending importance. Some sentences are dense (the double-backtick literals and the trailing frame-key clause), but nothing is filler.

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, the description does a decent job of describing what gets produced (a PNG texture plus a JSON hash map, and where they land). However, a packing tool's most consequential tuning knob, padding, is left unexplained, and there is no statement of what the call returns, so an agent can't fully reason about the result.

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

Parameters2/5

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

Schema coverage is 0%, so the description carries the full burden and only partially delivers: it explains what 'sprites' accepts (disk paths vs live sprite names) and clarifies out_json's default location. Neither out_png's role nor the padding parameter is explained anywhere, leaving half the parameters semantically undefined.

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: pack several sprites into one texture, including every frame, plus a JSON map in Aseprite's hash layout. That is concrete enough to separate it from single-file export siblings, though it never names an alternative export tool to contrast against.

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 context is implied rather than stated: the reader learns that sprites may be on-disk files or live open-sprite names, and that unsaved sprites cannot be named. There is no explicit when-to-use/when-not framing and no routing to or away from sibling export tools.

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