Skip to main content
Glama
Figma Local Bridge

Figma Local Bridge

by Miart

figma_cancel

Cancel a queued Figma write before it starts, returning OP_CANCELLED and leaving the document revision unchanged. Running operations cannot be interrupted; the refusal reports OP_RUNNING or OP_DONE.

Instructions

Stop a Figma operation that has NOT started (state queued in figma_ops) — the write a caller abandoned while it waited behind another write. Its caller is answered immediately with OP_CANCELLED and the document revision does not move, because nothing of it ran. A running call cannot be interrupted (Figma runs plugin code to completion): the refusal says which of OP_RUNNING / OP_DONE / OP_UNKNOWN it is, and OP_DONE names the revision the call actually reached. Read-only: cancelling only ever prevents a write.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "opId": "<opId>"
    },
    "name": "figma_cancel"
  }
}

Input Schema

NameRequiredDescriptionDefault
opIdYesOperation to stop, as figma_ops lists it or as a timeout error named it
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

A4.5/5.0
Behavior5/5

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 discloses that the caller is answered immediately with OP_CANCELLED, that the document revision does not move, that plugin code runs to completion so running ops are refused, and it enumerates the refusal codes OP_RUNNING / OP_DONE / OP_UNKNOWN with OP_DONE naming the reached revision. It also declares the read-only nature of cancellation, which is the key safety fact for a mutating-sounding verb.

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 sentences, front-loaded with the hard constraint on state and zero filler; every clause carries information. The long em-dash parentheticals make it denser than it needs to be, but no sentence could be deleted without losing a behavioral fact.

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 2-parameter tool with no annotations and no output schema, the description covers the success path, the failure codes, and the document-state guarantee, which is nearly everything an agent needs. It leaves minor gaps such as idempotency of repeated cancels and how to verify an op is still queued.

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 baseline is 3, but the description adds real meaning by tying `opId` to a specific valid state (`queued`) rather than any operation, which is the single most important semantic constraint on that parameter. `fileKey` adds nothing beyond the schema, which already names figma_whoami and figma_ping.

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 first clause gives a specific verb and resource ('Stop a Figma operation') and immediately constrains it to operations that have NOT started, citing the observable state (`queued` in figma_ops). An agent can distinguish this from any other figma_* write tool without opening a 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 states the precise use case (a write abandoned while queued behind another write) and the explicit exclusion (a running call cannot be interrupted), which is exactly the decision boundary an agent needs. It stops short of naming a companion tool for polling op state, so the agent must infer how to check whether an op is still queued before calling.

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