Skip to main content
Glama
Figma Local Bridge

Figma Local Bridge

by Miart

figma_inspect

Inspect a Figma node's compact structure and semantic fingerprint, and compare it against other nodes before any mutation. Disable the fingerprint when only structure is needed.

Instructions

Inspect a node: compact structure plus its semantic fingerprint. Pass compareWith to get EQUIVALENT / DIFFERENT / INCONCLUSIVE against other nodes BEFORE asking for any mutation. Set includeFingerprint:false when only the structure is needed — the fingerprint walks the whole subtree even at depth 1.

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_inspect"
  }
}

Input Schema

NameRequiredDescriptionDefault
depthNo
nodeIdNoDefaults to the current selection
policyNostrict
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.
compareWithNoNode ids to compare against
includeFingerprintNofalse skips the semantic subtree snapshot (compareWith still computes it)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.36.0

TDQS

A3.7/5.0
Behavior4/5

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

No annotations are supplied, so the description carries the full burden, and it does disclose real behavior: the fingerprint walks the entire subtree even at depth 1, and compareWith still computes the fingerprint when includeFingerprint is false. The phrase 'BEFORE asking for any mutation' implicitly establishes that inspection is non-mutating. It does not state whether results are cached or how large subtrees are truncated.

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?

Three tight sentences, front-loaded with the core action and the return shape, then the two conditional knobs. The em-dash aside is dense but earns its place; nothing is redundant.

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?

With no output schema, the description does name the comparison verdict vocabulary, which helps. However, for a 6-parameter inspection tool it leaves the 'policy' enum values and the depth/truncation tradeoff entirely unexplained, so an agent cannot reason about half the knobs.

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?

Adds genuine meaning beyond the 67%-covered schema: compareWith yields EQUIVALENT / DIFFERENT / INCONCLUSIVE verdicts, and includeFingerprint controls a costly subtree walk that compareWith overrides. The 'policy' enum (strict vs componentize) and the depth semantics remain undocumented in both places.

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 ('Inspect a node') plus exactly what it returns ('compact structure plus its semantic fingerprint'). It is distinguishable from figma_compare because it inspects one node and only optionally compares, but it never names a sibling to sharpen the boundary.

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 conditional usage advice: use compareWith before requesting a mutation, and turn off includeFingerprint when only structure is needed. That is mode-selection guidance rather than when-to-use-this-vs-another-tool guidance; it never explains why an agent would pick this over figma_compare or figma_get_selection.

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