Skip to main content
Glama
aseprite-claude-connector

aseprite-claude-connector

ask_point

Prompts the artist to click a canvas point—such as a pivot, anchor, or paint origin—and returns immediately so you can collect the click with get_asked_point.

Instructions

Live editor only: ask the ARTIST to click a point on the canvas (pivot, anchor, paint origin). Returns immediately; call get_asked_point to collect the click. Human-in-the-loop, in-editor.

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": "ask_point"
  }
}

Input Schema

NameRequiredDescriptionDefault
titleNoPick a point

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations only supply title and openWorldHint, so the description carries most of the burden and does well: it discloses that the call is non-blocking ('Returns immediately'), that a human must act, and that the result is retrieved separately. It stops short of timeout/abort behavior or what happens if the artist never clicks, which cancel_ask_point implies exists but the description never mentions.

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?

Four short clauses, opening with the hard constraint ('Live editor only') rather than burying it. The stray line breaks and trailing restatement 'Human-in-the-loop, in-editor' duplicate the scope already stated up front, costing a little.

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 an async human-in-the-loop tool with no output schema and thin annotations, the description supplies the critical facts: editor-only scope, immediate return, and the get_asked_point follow-up. Missing only edge-case behavior (never-clicked, cancellation) that would matter for robust agent use.

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 description coverage is 0% and the sole parameter 'title' is never mentioned in the description — its only documentation is the schema's type/default ('Pick a point'), which an agent can infer is a prompt label but not confirm. With just one optional, defaulted parameter the gap is minor, so this lands at baseline rather than being penalized heavily.

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 ('ask the ARTIST to click a point on the canvas') and grounds it with concrete examples (pivot, anchor, paint origin). The scope qualifier 'Live editor only' and the explicit pairing with get_asked_point make it distinguishable from generic point-mutation siblings without opening any schema.

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 use condition ('Live editor only', human-in-the-loop, in-editor) and names the exact follow-up call needed to complete the workflow: 'call get_asked_point to collect the click'. That is when-to-use plus the required next step, leaving nothing to inference.

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