Excaliself

Export drawing as .excalidraw file

export_scene

Read-only

Save a drawing as an .excalidraw raw scene JSON file that Excalidraw can open; optionally embed images as base64, with files over 10 MB refused.

Instructions

Exports a drawing as an .excalidraw file: the raw scene JSON that Excalidraw's "Save to file" writes, which Excalidraw and excalidraw.com open. The file comes back attached as an embedded resource; clients that save attachments give you a file path to copy from. To understand a drawing, use read_drawing instead.

Images are left out by default: their elements stay, but show as missing images. With includeImages they are embedded as base64, which can be large. Files over 10 MB are refused.

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_scene"
  }
}

Input Schema

Name	Required	Description	Default
`id`	Yes	A drawing id from list_drawings or search_drawings.
`includeImages`	No	Embed the drawing's images. Default false.

Schema Changelog

Changes observed during successful MCP inspections.

Addedv0.11.0Nov 10, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations only declare readOnlyHint=true; the description goes well beyond that by disclosing the return channel (file attached as an embedded resource, file path available for clients that save attachments) and the default-lossy behavior for images (elements remain but render as missing images). The base64 size warning and the 10 MB hard refusal are exactly the kind of operational constraints an agent cannot infer from annotations.

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?

Three short paragraphs, front-loaded with the format definition, then return channel, then the image-size caveat. Every sentence carries information an agent would otherwise have to discover by trial; nothing is redundant.

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?

With no output schema, the description correctly takes on the burden of explaining what comes back (embedded resource / file path) and the size limits. The only mild gap is behavior on invalid ids or drawings without images, but for a two-parameter read-only export this is close to complete.

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 adds real meaning: what 'off' actually means for images (elements kept, images render missing) and what 'on' costs (large base64 payloads, 10 MB ceiling). The 'id' parameter is not elaborated, but it is already fully described in the schema.

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 ('Exports a drawing as an .excalidraw file') and pins down the exact format: raw scene JSON matching Excalidraw's 'Save to file', openable by Excalidraw and excalidraw.com. That level of specificity lets an agent distinguish it from read_drawing and from generic export tools 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?

Explicitly routes away from itself for analysis tasks: 'To understand a drawing, use read_drawing instead.' It also gives conditional guidance on includeImages (default off, use it when images must survive). It does not state when to prefer it over other export-style siblings, but the named alternative and the conditional parameter advice cover the main selection decision.

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