Skip to main content
Glama
aseprite-claude-connector

aseprite-claude-connector

export_to_game

Exports Aseprite sprites into a Godot or Unity project, placing PNGs, sliced metadata, and animation resources in the correct assets folder for engine use.

Instructions

Export the sprite into a game project in one action, ready to select in the engine. game_dir is the project folder; it's remembered, so leave it out after the first time. Godot is detected from project.godot, Unity from Assets plus ProjectSettings, and any other folder gets a plain sheet. Art goes in the project's existing sprites or assets folder, or a new sprites (Assets/Sprites in Unity). Godot gets a PNG, plus a SpriteFrames .tres if animated. Unity gets a PNG and a pre-sliced .meta, using pixels_per_unit, and exporting again keeps the references to it working. name defaults to the sprite's file name. 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": "export_to_game"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileNo
nameNo
game_dirNo
pixels_per_unitNo

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 only declare destructiveHint=false, so the description carries most of the burden and does well: it discloses that files get written into the project's sprites/assets folder (creating one if absent), exactly what artifacts appear per engine (PNG, SpriteFrames .tres, pre-sliced .meta), that re-export preserves Unity references, and that game_dir is persisted between calls. It stops short of saying what happens when a same-named file already exists (overwrite vs. new file) and what the call returns.

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 action and outcome, then organized by concern (folder persistence, engine detection, per-engine artifacts, defaults, headless). It is dense but nearly every clause carries operational information; the engine-detection clause is slightly compressed and takes a read to parse.

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 4-optional-parameter write tool with no output schema and no parameter descriptions, the description covers engine detection rules, output layout, per-engine artifacts, defaults, and cross-call persistence. Remaining gaps are the meaning of `file` and the return value/overwrite behavior, which are minor but not zero for an agent verifying success.

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 description coverage is 0%, so the description must compensate and largely does: game_dir is explained as the project folder and as remembered/optional after the first call, name is given a default rule (sprite's file name), and pixels_per_unit is tied to Unity pre-slicing. The exception is `file`, which is only covered by the cryptic 'Headless: pass file' with no indication of what value it takes or what it controls.

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+resource+outcome: export the sprite into a game project 'in one action, ready to select in the engine.' The engine auto-detection detail implicitly separates it from the engine-specific siblings (export_godot, export_unity_sprite, export_gamemaker), but it never names or explicitly contrasts them, so an agent must infer the distinction.

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 rather than stated: 'in one action' suggests this is the auto-picking shortcut, and 'Headless: pass file' gives a situational cue. There is no explicit when-to-use/when-not-to-use guidance (e.g. 'use export_godot for explicit Godot-only export' or 'use batch_export for many sprites') despite a crowded set of export siblings.

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