Skip to main content
Glama
aseprite-claude-connector

aseprite-claude-connector

look

Read-only

Inspect an Aseprite canvas by returning a frame as a sharp-pixel image, with optional crop, layer isolation, selection, zoom, and background controls.

Instructions

See the canvas: returns a frame as an image, scaled up with sharp pixels. Defaults to the active frame with all visible layers. layer shows one layer or group alone (even if hidden). x/y/width/height crop to a region, and selection crops to the current selection. scale is an integer zoom (1-32); omit it to fit max_size. background is checker, transparent, or a #rrggbb color. Prefer a crop when you only need part of the canvas: images use up conversation space. 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": "look"
  }
}

Input Schema

NameRequiredDescriptionDefault
xNo
yNo
fileNo
frameNo
layerNo
scaleNo
widthNo
heightNo
max_sizeNo
selectionNo
backgroundNochecker

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?

readOnlyHint=true already establishes the safety profile, and the description adds genuinely useful behavior beyond it: hidden layers are still shown when ``layer`` is passed, scale is bounded to 1-32, omission of scale fits max_size, and images consume conversation space. It does not describe failure modes (e.g., out-of-range frame or layer names), which keeps it 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.

Conciseness4/5

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

The purpose and default behavior are front-loaded, and the cost warning about conversation space is a well-placed practical note. It is dense but nearly every clause carries parameter or behavior information; only the doubled-back ``background`` enumeration is slightly list-like.

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?

With no output schema and only a readOnlyHint annotation, the description does the heavy lifting well: what is returned (an image), how it is scaled, what defaults apply, and how to avoid oversized results. Minor gaps remain around error behavior for invalid frame/layer references, but nothing essential for a correct call is missing.

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

Parameters5/5

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

Schema description coverage is 0%, so the description carries the full burden for 11 parameters, and it addresses every one: x/y/width/height for cropping, selection as a selection-crop flag, layer as single-layer isolation, frame defaults, scale range, max_size fit behavior, background's three allowed forms (checker/transparent/#rrggbb), and file for headless use. This is meaning the schema alone would not convey.

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?

"See the canvas: returns a frame as an image, scaled up with sharp pixels" gives a specific verb and resource and states the output type immediately. It does not differentiate itself from the sibling viewers look_animation and look_onion, so an agent must infer which viewer applies to animation/onion-skin cases.

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?

It gives concrete usage advice: "Prefer a crop when you only need part of the canvas: images use up conversation space," and notes the default (active frame, all visible layers) plus the headless path via ``file``. It stops short of naming alternative tools or when not to use this one, so the sibling routing is 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