Skip to main content
Glama
aseprite-claude-connector

aseprite-claude-connector

add_fire

Creates looping animated fire with swaying flames and rising embers on a new Aseprite layer, optionally adding campfire logs and stones for pixel-art sprites.

Instructions

Light a fire with the middle of its base at x, y: flames height pixels tall that lick and sway, and embers that rise above them and lean with wind (pixels; negative blows left). It loops seamlessly over the sprite's frames, so give it 8 or more; with one frame it is a still. logs lays crossed logs and a ring of stones, for a campfire; leave them off for a torch or a brazier. palette is fire, blue, or green. It goes on a new layer named layer on top. Follow with add_glow at the same place to light what is round it. 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": {
      "x": "<x>",
      "y": "<y>"
    },
    "name": "add_fire"
  }
}

Input Schema

NameRequiredDescriptionDefault
xYes
yYes
fileNo
logsNo
seedNo
windNo
layerNoFire
heightNo
paletteNofire

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4.1/5.0
Behavior3/5

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

With only a title annotation, the description carries the full burden and does disclose key side effects: it creates a new layer on top, produces one undo step, and loops across the sprite's frames. It is silent on what happens if the named layer already exists, whether output is deterministic from 'seed', and what the call returns, which matters for a 9-parameter mutating drawing tool.

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 coordinates, then parameter behavior, then workflow hints, so an agent can stop reading early. The prose is dense but nearly every clause conveys a usable fact; the ember/'lick and sway' imagery is the one expendable flourish.

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 9-parameter generative tool with no annotations and no output schema, the description covers the anchor, sizing, wind, palette, log decoration, layer placement, frame loop, undo cost, and headless mode. The remaining gaps (seed reproducibility, layer-name collision behavior) are real but narrow.

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: units for height (pixels), wind direction ('negative blows left'), the base-anchoring of x/y, the enumerated palette values (fire, blue, green), the layer name, and the toggle semantics of logs. Only 'seed' is left unexplained and 'file' is mentioned only as a headless requirement.

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 ('Light a fire') plus the anchor point ('middle of its base at x, y') and the visual result (flames, embers). It also differentiates itself from the nearest sibling by naming add_glow as the follow-up pass rather than a substitute.

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 concrete when-to-use branches: 'logs' for a campfire, omit for a torch or brazier, and 'give it 8 or more' frames for a seamless loop versus a still at one frame. It also states the headless path ('pass file'). It does not cover when to prefer this over other decorative passes such as add_glow or add_mist beyond the pairing note.

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