Skip to main content
Glama

Draw or edit an image

open_paint
Read-onlyIdempotent

Open a Paint-style editor. Omit imageUrl for a blank white canvas, or provide a public HTTPS image URL or an existing base64 image data URI (PNG/JPEG/WebP), up to 5 MiB. Do not manually reconstruct or generate base64; users can open local files using File > Open when no URI is available. Width and height are requested maximum blank dimensions; the initial bitmap is reduced to fit the editor if needed. Always call the app-provided get_canvas tool after opening and before drawing to obtain actual dimensions and valid coordinates. Use resize_canvas for exact dimensions. Imported images up to 4096 × 4096 are proportionally resized down to fit the editor at normal zoom, capped at 1024 × 768; smaller images are not enlarged. Saved images use the resized dimensions. The File menu offers Download, Copy to clipboard, and Send to chat. Download uses host-managed downloads when available. Copy to clipboard requires clipboard access. Send to chat uses image messages or image context updates when supported. Temporary image sharing is enabled: text-capable clients receive a 24-hour reference retrievable with get_saved_image; Download can alternatively open a temporary HTTPS download URL directly through the host openLinks capability. This tool opens the editor; it does not return a finished drawing immediately. Conversation attachments must be supplied explicitly; the app cannot access them automatically.

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": "open_paint"
  }
}

Input Schema

NameRequiredDescriptionDefault
titleNoDrawing
widthNo
heightNo
imageUrlNoA public HTTPS image URL, or an existing base64 image data URI (PNG/JPEG/WebP, up to 5 MiB). HTTPS URLs are limited to 16,000 characters. Omit for a blank canvas. Do not manually reconstruct or generate base64 from an image; use File > Open for local files when no URI is available.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Goes far beyond the annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint), disclosing the 5 MiB / 4096×4096 limits, the 1024×768 downscale cap, no-upscaling behavior, permission requirements for clipboard access, and the 24-hour temporary image reference. It also correctly warns that conversation attachments are not auto-accessible, which is real behavioral context an agent needs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded, but the body is a dense run-on that repeats the imageUrl constraints already in the schema and repeats "do not reconstruct base64" verbatim from the schema description. Sentences are long and mix sizing rules, export mechanics, and sharing behavior without much grouping.

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 complex, open-ended tool with no output schema, the description covers sizing, required follow-up calls, export paths, and sharing limitations thoroughly. The only meaningful omission is the title parameter's role, which is minor given the editor's default.

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 coverage is only 25%, so the description must carry weight, and it does: width/height are explained as requested maximum blank dimensions subject to fitting, and imageUrl constraints are restated with the local-file alternative. The title parameter is never mentioned, which is the one clear gap.

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?

Uses a specific verb and resource ("Open a Paint-style editor") and explicitly clarifies it "does not return a finished drawing immediately," which distinguishes it from an image-generation tool. It could be sharper about how it relates to the sibling get_saved_image, which it only mentions deep in a sharing-behavior sentence.

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 concrete when-to-use branches: omit imageUrl for a blank canvas, supply an HTTPS URL or data URI, or use File > Open for local files. It also names the follow-up tools (get_canvas before drawing, resize_canvas for exact dimensions). Missing explicit exclusions for when not to use the editor at all, so it is not a full 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources