Skip to main content
Glama
aseprite-claude-connector

aseprite-claude-connector

lift_symbols

Moves floating symbols off a character layer onto a separate layer, then animates them per frame while removing them from the original layer.

Instructions

Move floating symbols ("!", "?", Zzz, hearts, sparkles) off a character's layer onto a new layer, and animate them there. boxes are [x, y, w, h] round each symbol (or group); only pixels not joined to the body are taken, so a box can overlap a wing. They're found on from_frame and erased from every frame of layer. keys, one per frame (frames are made as needed): {"frame": 2, "symbols": [[dx, dy], null], "ms": 100}, an offset per box, or null to hide it. Frames without a key show them in place. One undo step. Headless: pass file.

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": {
      "boxes": "<boxes>"
    },
    "name": "lift_symbols"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileNo
keysNo
nameNoEffects
boxesYes
layerNo
from_frameNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A3.6/5.0
Behavior4/5

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

No functional annotations exist, so the description carries the burden and mostly delivers: it discloses the masking rule ("only pixels not joined to the body are taken, so a box can overlap a wing"), the destructive scope ("erased from every frame of ``layer``"), frame auto-creation, default placement for unkeyed frames, null semantics for hiding, and "One undo step." Undisclosed: the return value and what happens if the target layer name already exists.

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 core action, then detail in decreasing order of importance, ending with the headless note. Every clause carries information, though the dense inline code spans and parenthetical asides make it read like reference notes rather than prose. Slightly cramped but no wasted sentences.

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 6-parameter mutation tool with no annotations and no output schema, the description covers the destructive scope, undo behavior, frame generation, and key format that an agent needs to call it safely. Remaining gaps are the undocumented ``name`` parameter and the return shape after lifting.

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 it largely does: it defines ``boxes`` as ``[x, y, w, h]``, gives a concrete ``keys`` example including the ``ms`` and null-to-hide semantics, and explains ``from_frame``, ``layer``, and ``file``. Only ``name`` (default "Effects") is left entirely unexplained, which is a minor gap for 6 parameters.

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?

States a specific verb and resource: "Move floating symbols ... off a character's layer onto a new layer, and animate them there," and enumerates the symbol types ("!", "?", Zzz, hearts, sparkles). It's easy to tell apart from effect-adding siblings like add_glow or add_mist. It does not explicitly contrast with any sibling, keeping it at 4.

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

Usage Guidelines2/5

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

No when-to-use guidance, no prerequisites, and no alternatives named. The only contextual cue is the operational note "Headless: pass ``file``," which is about invocation mode rather than tool selection. An agent learns what it does but not when to reach for it over another effect or layer tool.

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