Skip to main content
Glama
Figma Local Bridge

Figma Local Bridge

by Miart

figma_get_metadata

Retrieve a lightweight XML outline of a Figma node, page, or selection—including type, ID, name, position, and size—to find node IDs before fetching design context or screenshots.

Instructions

Sparse XML outline of a node/page/selection: type, id, name, position and size. Cheap; use it to find ids before get_design_context or get_screenshot.

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": "figma_get_metadata"
  }
}

Input Schema

NameRequiredDescriptionDefault
depthNo
nodeIdNoDefaults to the single selected node, else the current page
fileKeyNoWhich connected Figma file to use: its fileKey (figma_whoami) or, when omitted, the only connected file. Required once more than one file is connected; figma_ping lists them.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.36.0

TDQS

A3.9/5.0
Behavior3/5

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

With no annotations, the description carries the full burden and does add real context: output is a sparse XML outline with a known field set, and the call is cheap relative to siblings. However, it says nothing about read-only guarantees, permissions/auth requirements, rate limits, or size of the returned tree, which matters for a tool that defaults to depth 6.

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 tight sentences, front-loaded with the output shape and ending with the routing advice; every clause carries information. Minor density in the field list, but nothing extraneous.

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 3-parameter, no-output-schema read tool, the description tells the agent what comes back and how the call fits into a workflow before heavier siblings. The remaining gap is depth semantics and any statement of read-only/permission behavior, which no other structured field covers.

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 coverage is 67%, with fileKey and nodeId already documented in the schema; the description's mention of 'node/page/selection' only loosely corroborates nodeId's default behavior. The depth parameter has no meaning explained in either the schema or the description, so the agent gets no guidance on tree expansion cost or trimming.

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 concrete verb+resource ('Sparse XML outline of a node/page/selection') and enumerates the returned fields (type, id, name, position, size), which is more than the name alone conveys. It also distinguishes itself from get_design_context and get_screenshot by framing itself as the lightweight id-lookup step.

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 an explicit usage pattern: call this first to find ids 'before get_design_context or get_screenshot', reinforced by the 'Cheap' cost hint. It lacks an explicit when-not statement (e.g., don't use it if you already have ids or need styles/colors), so it falls one step short of full coverage.

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