Skip to main content
Glama
aseprite-claude-connector

aseprite-claude-connector

frame_diff

Read-only

Compare two composited frames pixel by pixel to count changed pixels, report change bounding box, and confirm whether they are identical for verifying animation movement or catching unintended edits.

Instructions

Pixel-exact diff of two composited frames: changed-pixel count and ratio, the bounding box of the change, and whether they're identical. Use it to verify an animation actually moves — or that an edit didn't leak into frames it shouldn't touch. 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": {
      "frame_a": "<frame_a>",
      "frame_b": "<frame_b>"
    },
    "name": "frame_diff"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileNo
frame_aYes
frame_bYes

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?

Annotations already declare readOnlyHint=true, and the description adds real context beyond that: the comparison is pixel-exact on composited output, and it discloses the exact return fields so the agent knows what evidence it will get back. The 'Headless: pass file' note flags a mode-dependent requirement that annotations do not cover.

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?

Three sentences, front-loaded with the operation and its outputs before the use cases, ending with the terse mode caveat. No filler or restatement of the name.

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?

No output schema exists, but the description enumerates the return payload itself, and the read-only nature is covered by annotations. The remaining gap is parameter detail (index semantics, ordering) for a 0%-coverage schema, which is minor for a two-frame comparison tool.

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

Parameters3/5

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

Schema coverage is 0% for three parameters, so the description must compensate. It does partially: 'two composited frames' ties frame_a/frame_b to frame identities, and 'Headless: pass file' explains when the optional file argument is needed. It never states that frame_a/frame_b are integer indices, whether order matters, or what happens with identical or out-of-range indices.

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 — 'pixel-exact diff of two composited frames' — and enumerates the outputs (changed-pixel count, ratio, bounding box, identical flag). 'Composited' distinguishes it from per-layer operations, so an agent can tell it apart from mutation siblings like add_frame or smear_frame.

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 two concrete triggering scenarios: verifying an animation actually moves, and checking that an edit didn't leak into unrelated frames. No explicit exclusions or named alternatives, but the use cases are unambiguous and no sibling appears to compete for the same task.

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