Skip to main content
Glama
Figma Local Bridge

Figma Local Bridge

by Miart

figma_ops

Inspect live Figma plugin operation state—running, queued, or finished calls—and settle timed-out operations by opId without re-reading the document. Read-only.

Instructions

What the Figma plugin is doing right now, per file: the call that is RUNNING, the writes QUEUED behind it, and what finished recently — plus, for this MCP session, the calls it is still waiting for and the ones it gave up on. Pass an opId (timeout errors name it) to get that operation's state and its recorded answer, which is how a call that timed out is settled without re-reading the document. Read-only.

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_ops"
  }
}

Input Schema

NameRequiredDescriptionDefault
opIdNoAsk about one operation: its state, and the answer recorded for it (what a caller that timed out never saw)
recentNoHow many finished operations to list, newest first
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
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does so well: it declares 'Read-only,' explains the split between per-file state and per-MCP-session state, and discloses that a recorded answer can be retrieved after a timeout. It does not discuss staleness of the plugin view or any limits on how far back finished operations are retained.

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?

The current-state summary is front-loaded and the timeout/opId workflow follows immediately, so an agent gets the mental model before the instructions. It is dense and runs long in a single flowing sentence, but each clause (running, queued, finished, pending, abandoned) carries distinct information.

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?

There is no output schema, so the description must convey return content, and it does: operation state, queued writes, recent completions, session-pending and abandoned calls, and the recorded answer for an opId. Missing only peripheral detail such as ordering/format of the returned states beyond 'newest first,' which the schema covers for recent.

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 100%, so all three parameters are already documented in the schema, establishing a baseline of 3. The description only reinforces opId, adding the useful note that timeout errors name it; recent and fileKey semantics are left entirely to the schema.

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?

The description uses precise operational language ('the call that is RUNNING, the writes QUEUED behind it, and what finished recently') to characterize the tool as a per-file plugin-activity reporter, plus a per-session view of pending and abandoned calls. It is clearly not a document reader or editor, which separates it from most siblings, but it never explicitly frames itself against near-neighbors such as figma_journal or figma_cancel.

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?

It gives a concrete triggering condition and outcome: 'Pass an opId (timeout errors name it) to get that operation's state and its recorded answer, which is how a call that timed out is settled without re-reading the document.' That is genuine when-to-use guidance. It stops short of stating when not to use it or naming an alternative tool for adjacent needs.

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