Skip to main content
Glama
aseprite-claude-connector

aseprite-claude-connector

save_all_sprites

Saves open Aseprite sprites to a specified folder as .aseprite files, copying unsaved or changed sprites so closing tabs does not lose work and existing files remain untouched.

Instructions

Live editor only: save open work into folder as .aseprite files, so nothing is lost when tabs are closed. Unsaved sprites are saved there and become those files (named after their first tag); sprites that already have a file and unsaved changes are COPIED there, leaving their own file untouched. all_sprites copies unchanged ones too. only limits it to sprites with these filenames or tags. Never overwrites: a taken name gets a number.

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": {
      "folder": "<folder>"
    },
    "name": "save_all_sprites"
  }
}

Input Schema

NameRequiredDescriptionDefault
onlyNo
folderYes
all_spritesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations only carry a title and openWorldHint, so the description bears most of the behavioral burden and does so well: it distinguishes saving an unsaved sprite from copying a modified already-filed sprite, states that the original file is left untouched, and guarantees no overwrite via numeric suffixing. It does not say whether the target folder must already exist or what is returned, which keeps it short of 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?

Front-loads the precondition and purpose, then spends its remaining sentences on exactly the distinctions an agent needs (save vs copy, all_sprites, only, overwrite policy). Dense but every clause carries decision-relevant 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?

For a three-parameter mutation with no output schema and thin annotations, the description covers side effects, filtering, and collision handling thoroughly. It stops short of describing the result of the call (e.g. which paths were written) or failure modes for an invalid folder.

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%, and the description compensates by giving all three parameters meaning: folder as the .aseprite destination, all_sprites as including unchanged sprites, and only as a filter on filenames or tags. It does not specify folder path requirements (absolute vs relative, existence, creation), so coverage is strong but not exhaustive.

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 concrete verb and resource ('save open work into folder as .aseprite files') plus the scope that separates it from a single-sprite save, and explains why it exists ('so nothing is lost when tabs are closed'). An agent can tell this is a bulk, live-editor save without opening the schema.

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 a clear precondition ('Live editor only') and explains when to reach for the optional flags ('all_sprites copies unchanged ones too', 'only limits it to sprites with these filenames or tags'). It never names a sibling such as save_sprite as the single-sprite alternative, so routing is implied rather than explicit.

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