Skip to main content
Glama
aseprite-claude-connector

aseprite-claude-connector

set_tiles

Places tile references on a tilemap layer's cel at specified frame and grid cells, creating or growing the cel as needed for one-undo tilemap edits.

Instructions

Place tile references on a tilemap layer's cel. tiles is a list of {column, row, index} objects (0-based grid cells; index 0 erases to the empty tile). The cel is created or grown as needed, anchored at the sprite origin. frame is 1-based. 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": {
      "layer": "<layer>",
      "frame": "<frame>",
      "tiles": "<tiles>"
    },
    "name": "set_tiles"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileNo
frameYes
layerYes
tilesYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4.2/5.0
Behavior4/5

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

With only a title annotation, the description carries the burden well: it discloses that the cel is created or grown as needed, is anchored at the sprite origin, that index 0 erases, that frame is 1-based, and that the operation is a single undo step. Missing are error behavior for an invalid index or non-tilemap layer, and any note about return value, which keeps this from a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Five short sentences, front-loaded with the action and followed by exactly the semantics an agent cannot get from the schema. No filler, no repetition of the tool name, and the headless note is placed last where a mode-specific caveat belongs.

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-parameter mutation tool with no annotations and no output schema, this covers the important ground: input structure, coordinate conventions, side effects (cel growth, undo), and headless invocation. The remaining gap is failure modes and whether anything is returned, which is minor given no output schema exists.

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 does: it defines the shape of ``tiles``, the 0-based grid convention, the erase sentinel, the 1-based ``frame``, and the purpose of ``file``. Only ``layer`` is left undefined, and its meaning is largely carried by the 'tilemap layer's cel' phrasing.

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 with scope: 'Place tile references on a tilemap layer's cel.' The agent immediately knows this is a tilemap write operation rather than a sprite/layer property setter, and the '{column,row,index}' detail confirms the granularity of the write.

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: no explicit when-to-use versus alternatives, and no sibling does the same job so no routing is needed. The one real directive is 'Headless: pass ``file``', which tells the agent how to invoke it in headless mode, but preconditions (layer must exist, must be a tilemap layer) are left implicit.

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