Skip to main content
Glama
aseprite-claude-connector

aseprite-claude-connector

watch_changes

Start tracking artist edits to the active Aseprite sprite, then poll for changes so you can wait until touch-ups finish before rerunning QA checks.

Instructions

Live editor only: start counting edits the ARTIST makes to the active sprite (via Sprite.events). Poll with get_watched_changes — e.g. wait for the artist to finish touching up, then re-run the QA sweep.

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": "watch_changes"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4.6/5.0
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 the live-editor-only scope, that counting is non-blocking and must be polled, and critically that it counts the artist's edits rather than the agent's own. It does not say whether a second watch resets a counter, how long counting persists, or how to stop, which is the remaining gap.

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?

Two sentences, no filler, with the hard constraint ("Live editor only") front-loaded before the workflow hint. Every clause adds actionable information.

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 and no annotations, so the description must imply what comes back; it does so by directing the agent to poll get_watched_changes. It is nearly complete for a zero-parameter stateful watcher, missing only counter lifetime/reset semantics.

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?

The tool takes zero parameters, so there is nothing for the description to clarify beyond the schema; baseline applies. The description reinforces the no-argument nature implicitly by scoping the watch to the active sprite.

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+resource: it starts a counter of artist-made edits to the active sprite, and explicitly attributes the edits to the ARTIST via Sprite.events. That distinguishes it cleanly from get_watched_changes (polling) and from tools that mutate the sprite themselves.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit precondition ("Live editor only"), names the companion polling tool, and supplies a concrete workflow ("wait for the artist to finish touching up, then re-run the QA sweep"). An agent knows both when to call it and what to call next.

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