Skip to main content
Glama

Export drawing as image

export_drawing
Read-only

Exports a drawing as a PNG or SVG image file for documentation, READMEs, or slides, returning it as an attachment clients can save.

Instructions

Exports a drawing as an image file, as Excalidraw's "Export image" does, for documentation, a README, or slides. The file comes back attached: PNG as image content, SVG as an embedded resource. Clients that save attachments give you a file path to copy from.

"png" (default) is a bitmap that every client can show. "svg" stays sharp at any size and embeds the drawing's fonts, so it looks the same anywhere, even in an .

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": {
      "id": "<id>"
    },
    "name": "export_drawing"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesA drawing id from list_drawings or search_drawings.
scaleNoSize multiplier. Default 2 for PNG (sharp on high-density screens), 1 for SVG.
formatNoDefault "png".png
paddingNoSpace around the drawing, in pixels. Default 10.
darkModeNoDark mode, as the canvas shows it. Default false.
backgroundNoFill the canvas color behind the drawing. false gives a transparent background. Default true.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.11.0

TDQS

A4/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=true, so the description carries the rest — and it does, explaining that the file returns attached (PNG as image content, SVG as an embedded resource) and that clients saving attachments yield a file path. That delivery detail is exactly the behavior an agent cannot otherwise infer, with no output schema to fall back on. It omits any failure modes or size limits.

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?

Two short paragraphs, front-loaded with the verb and resource, then the output-delivery detail, then format guidance. Nearly every sentence earns its place; the Excalidraw comparison and the list of use cases are mildly redundant with each other but helpful framing.

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 6-parameter, 100%-covered tool with no output schema, the description fills the key gap by explaining how the export is returned to the client. The remaining omission is sibling positioning against export_scene, which leaves the agent to infer which export tool handles which payload.

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 100%, so the baseline is 3, but the description goes beyond it by explaining the trade-offs behind format and the rationale for scale defaults (2 for PNG to stay sharp on high-density screens, 1 for SVG). Padding, darkMode, and background are left entirely to the 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?

States a specific verb and resource ("Exports a drawing as an image file") and grounds it in a familiar reference ("as Excalidraw's 'Export image' does"), so the agent knows exactly what it produces. It does not distinguish itself from the sibling export_scene, which an agent could reasonably confuse with a drawing export.

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 use cases (documentation, a README, slides) and, more usefully, spells out when to choose png versus svg — bitmap for universal display, svg for resolution independence and embedded fonts. It stops short of stating when *not* to use this tool or naming export_scene as the alternative for non-image exports.

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