Skip to main content
Glama
Figma Local Bridge

Figma Local Bridge

by Miart

figma_journal

Review local Figma bridge call history to diagnose timed-out, dropped, or late plugin responses after restarts, with filters for method, file, and unsettled outcomes.

Instructions

The bridge's own history, from a local append-only JSONL file: every call it sent to a Figma plugin — method, target, outcome, revision — and above all the ones that did not end cleanly: timeout (the caller gave up), dropped (no answer at all: may or may not have been applied) and late (the answer that arrived after the caller stopped listening). It survives bridge and plugin restarts, which is exactly where figma_ops stops helping. Read-only and entirely local: snippets, text and images are never recorded — only method names, target ids, revisions and outcomes. Lives in ~/.local/share/opencode/figma-bridge-journal/ops.jsonl (FIGMA_BRIDGE_JOURNAL_DIR moves it, FIGMA_BRIDGE_JOURNAL=0 switches recording off).

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_journal"
  }
}

Input Schema

NameRequiredDescriptionDefault
lastNoHow many matching lines to return, taken from the tail; returned oldest-first
methodNoOnly entries for this plugin method (e.g. use_figma)
fileKeyNoOnly entries for this fileKey
unsettledNoOnly the calls that did not end with a clean answer: `timeout`, `dropped`, and `late`

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.36.0

TDQS

A4.5/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does: read-only, entirely local, no snippets/text/images recorded, persistence across restarts, file location, and the two environment variables that relocate or disable recording. It also defines the three failure outcomes precisely, including the ambiguous 'dropped' case (may or may not have been applied), which is exactly the nuance an agent needs.

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 dense sentences, front-loaded with what the tool is, followed by the failure-mode detail that justifies it, then storage and privacy. Every sentence carries information, though the parenthetical outcome definitions make it longer than strictly needed for a scan.

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 return shape must come from the description, and it does list the recorded fields plus the guarantees about what is never stored. A few details remain implicit, such as the line format and timestamps per entry, but nothing an agent needs in order to call it correctly is missing.

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; the description adds value by spelling out the meaning of the outcome vocabulary that back-filters `unsettled` (timeout = caller gave up, dropped = no answer, late = answer after the caller stopped listening) and by naming the record fields that `method` and `fileKey` filter against. It does not add syntax or edge-case guidance for `last` beyond what the schema already documents.

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?

The description states a specific resource and scope: the bridge's own call history from a local append-only JSONL file, containing method, target, outcome and revision. It explicitly distinguishes itself from figma_ops ('exactly where figma_ops stops helping'), so an agent can tell it apart from the live operation tool without opening either 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?

It gives clear context for when this tool is the right one: recovering history that survives bridge and plugin restarts, and especially diagnosing calls that ended as timeout, dropped, or late. It names figma_ops as the contrasting tool. It does not state explicit exclusions or preconditions beyond that, which keeps it short of a 5.

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