Skip to main content
Glama
aseprite-claude-connector

aseprite-claude-connector

change_summary

Read-only

Summarizes recent Aseprite edits from this session, showing repeats, touched frames and layers, and pixel changes; use the optional limit to focus on the latest edits.

Instructions

A short list of what Claude changed this session, oldest first: each edit, how many times in a row, the frames and layers it touched, and pixels changed. Repeats on the same layer are merged. last limits it to the most recent edits. It covers the most recent 500 edits since the server started, and frames are missing for edits made with the pixel cap off, or that can't lose pixels.

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": "change_summary"
  }
}

Input Schema

NameRequiredDescriptionDefault
lastNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A3.7/5.0
Behavior4/5

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

Beyond readOnlyHint=true, the description discloses several non-obvious behaviors: results are ordered oldest first, repeats on the same layer are merged, only the most recent 500 edits since server start are retained, and frames are omitted for edits made with the pixel cap off or that cannot lose pixels. Those are real caveats an agent would otherwise get wrong. It stops short of covering pagination or cost, hence 4 rather than 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?

What the tool returns is front-loaded in the first clause, then caveats follow in descending importance. Sentences are dense but each contributes a distinct fact. The only mild inefficiency is the trailing conditional about missing frames, which is wordy relative to its value.

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 one optional parameter, no output schema, and only readOnlyHint for annotations, the description is the main source of truth, and it does describe the record shape and retention limits. An agent could call it correctly from this text. Missing only the exact semantics of `last` and whether an empty result is possible.

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?

The schema gives `last` zero description coverage, so the description carries the burden, and it does explain that `last` limits results to the most recent edits. It does not say whether the value is a count of edits or a time window, nor how it interacts with the 500-edit cap. That is partial compensation for a bare schema.

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?

The description names a concrete output: an oldest-first list of what changed this session, broken into edits, repeat counts, frames, layers, and pixel counts. That is far more specific than restating the name. It does not contrast itself with any sibling, but its read-only audit role is distinctive enough that confusion is unlikely.

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 only implied: an agent can infer this is for reviewing what changed recently, and the `last` parameter is framed as narrowing to the most recent edits. There is no explicit statement of when to prefer this tool over other inspection tools, nor any when-not guidance.

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