Skip to main content
Glama
Figma Local Bridge

Figma Local Bridge

by Miart

figma_audit

Audits a Figma page or subtree read-only for design-system issues—duplicate keys, hardcoded styles, unstyled text, contrast failures, detached instances—and returns node-level findings.

Instructions

Read-only design-system audit of a page or subtree. Reports stable-key problems (duplicate keys, nodes added to a built tree without a key), literal fills/strokes that are neither a style nor a variable, text without a text style, placeholder copy, detached instances, WCAG AA contrast against the effective background, default layer names, and (opt-in) empty text, literal effects, off-scale spacing and off-scale radius. Every finding carries nodeId, stable key, name, type, path, rule, severity and the value that caused it. With suggest:true (default) a hardcoded colour also carries exact local paint-style and colour-variable candidates, and unstyled text carries exact local text-style candidates; spacing/radius findings name the nearest on-scale value. It never edits the document.

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_audit"
  }
}

Input Schema

NameRequiredDescriptionDefault
rulesNoRules to run. Defaults to duplicate-key, unkeyed-node, hardcoded-fill, hardcoded-stroke, unstyled-text, placeholder-text, detached-instance, contrast, default-name. Add spacing, radius, empty-text or hardcoded-effect explicitly.
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.
suggestNoAttach exact local paint-style, colour-variable and text-style candidates to findings; never applies them
maxNodesNoStop after this many visible nodes
rootNodeIdNoPage or subtree to audit; defaults to the current page
maxFindingsNoList at most this many findings; counts are still complete
radiusScaleNoAllowed corner radii
spacingScaleNoAllowed spacing values, e.g. [0,4,8,12,16,24,32]. When omitted, spacingMultiple is used.
includeHiddenNoAudit hidden layers too
radiusMultipleNoOff-scale radius means not a multiple of this
spacingMultipleNoOff-scale spacing means not a multiple of this

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.36.0

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does well: it declares the tool is read-only, never edits the document, and specifies the exact fields each finding carries (nodeId, key, name, type, path, rule, severity, value). It omits permission/auth requirements and any rate or performance characteristics beyond the maxNodes cutoff described in the schema.

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?

Front-loaded with purpose and scope, then rules, then output shape, then the suggest behavior and the no-edit guarantee. Dense but nearly every sentence carries information; the long rule enumeration is the only place that could be tightened.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 11-parameter tool with no annotations and no output schema, the description covers purpose, safety, output fields and suggestion behavior. However, several parameters (fileKey selection, maxFindings versus complete counts, includeHidden, rootNodeId defaults) are only explained in the schema, leaving the description short of fully self-contained.

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 meaning beyond the schema: it explains that suggest:true attaches exact local paint-style, colour-variable and text-style candidates without applying them, and that spacing/radius findings name the nearest on-scale value.

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?

Opens with a specific verb and resource ('Read-only design-system audit of a page or subtree') and then enumerates the exact rules it reports, so an agent can tell this apart from inspection or design-system listing 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?

States the read-only nature and that it never edits, and flags which rules are default versus 'opt-in' (empty text, literal effects, off-scale spacing/radius), which is real when-to-use guidance. It stops short of naming when to prefer a sibling like figma_inspect or figma_design_system instead.

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