Skip to main content
Glama

Download assets

figma_local_download_assets
Read-only

Download exported images, original fill images, and SVG vector assets for a single Figma node, using its export settings or overriding format and scale.

Instructions

Download assets for a single node: export (an exported image of the whole node), rawImages (original uploaded images used as fills in the subtree, capped at 20, each with its real format) and svgAssets (SVGs for vector layers such as icons and logos, capped at 20). When defaultFormat/defaultScale are given they override the export settings configured on the node; otherwise the node's export settings are used if present, else png at scale 1. Pass them only when the user asks for a specific format or size. Each asset has a temporary url (download promptly) or, when the companion plugin rendered it, a local file path.

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": {
      "fileKey": "<fileKey>",
      "nodeId": "<nodeId>"
    },
    "name": "figma_local_download_assets"
  }
}

Input Schema

NameRequiredDescriptionDefault
nodeIdYesThe ID of the node in the Figma document, eg. "123:456" or "123-456". Extract it from the URL's node-id query parameter. Do not pass an empty or guessed nodeId.
fileKeyYesThe key of the Figma file to use. If a URL is provided, extract the file key from it: for https://figma.com/design/:fileKey/:fileName?node-id=1-2 the fileKey is `:fileKey`. For https://figma.com/design/:fileKey/branch/:branchKey/:fileName use the branchKey. A full URL is also accepted.
defaultScaleNoExport scale (resolution multiplier). Overrides the node's export settings.
defaultFormatNoExport format. Overrides the node's export settings.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

With readOnlyHint/openWorldHint already covering the safety profile, the description still contributes non-obvious behavior: the 20-asset caps on rawImages and svgAssets, the precedence of defaultFormat/defaultScale over node settings, the png@1 fallback, and above all the fact that each asset carries either an expiring `url` or a local `file` path depending on whether the companion plugin rendered it. That URL-expiry warning is exactly the kind of operational detail annotations cannot express. It stops short of describing failure modes for nodes that cannot be exported.

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 content is dense and front-loaded with the three asset types, which is the right ordering, but it arrives as a single run-on block that packs caps, fallback ordering, and URL-lifetime warnings into the same sentence. It is not padded, yet the structure makes it easy to miss the temporary-URL warning buried at the end.

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 tool with no output schema, the description does the heavy lifting of describing return shape (url vs. file path, per-asset format) and the caps that constrain results. What is missing is edge-case coverage: behavior for nodes with no exportable content, and whether partial results are returned when the 20-item cap is hit.

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 already 100%, so the baseline is 3, and the description adds genuine semantic value on top: the two override parameters are explained as precedence rules over the node's configured export settings, with a behavioral instruction about when a caller should supply them. The required fileKey/nodeId parameters get no mention in prose, but their schema descriptions are already thorough.

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 clear verb+resource (download assets for a single node) and enumerates the three asset buckets it can return, each with a short parenthetical explanation of what it contains. It never names or contrasts against siblings such as figma_local_get_screenshot, so an agent must infer the boundary from the asset-type vocabulary alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives real conditional guidance for the override parameters ("Pass them only when the user asks for a specific format or size") and explains the fallback chain when they are absent. It does not say when to choose this tool over the export-style siblings, nor does it state prerequisites or exclusions, so the when-to-use signal is only partially present.

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