Skip to main content
Glama
Figma Local Bridge

Figma Local Bridge

by Miart

figma_set_selection

Select Figma nodes and scroll them into view so users can immediately see the result—without hunting across a large canvas. Changes editor state only, not the document.

Instructions

Select nodes in the Figma editor and scroll them into view. The only way to move the user's cursor — use it to hand work over ('look at what I just built') instead of making them hunt for it on a huge canvas. Editor state only; the document is not modified.

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": {
      "nodeIds": "<nodeIds>"
    },
    "name": "figma_set_selection"
  }
}

Input Schema

NameRequiredDescriptionDefault
zoomNoScroll and zoom the viewport to the selection
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.
nodeIdsYesNode ids to select

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 full burden and does well: it discloses that this mutates editor/viewport state but not the document, and that it moves the user's cursor/selection — the most important side effect for an agent to know. It omits whether an existing selection is replaced and what happens with invalid node ids, keeping it short of a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the action and followed by the differentiating use case and the side-effect boundary. Every clause earns its place with no restatement of the schema.

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 three-parameter, no-output-schema tool, the description covers purpose, the handoff use case, and the critical non-destructiveness guarantee. Remaining gaps (selection replacement behavior, invalid-id handling, multi-file requirement) are partly covered by the schema's fileKey description, so completeness is high but not exhaustive.

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 description coverage is 100%, so all three parameters are already documented in the schema, including the fileKey/file-disambiguation rules. The description only loosely connects to the zoom parameter via 'scroll them into view' and adds no syntax or format detail beyond the schema — baseline 3.

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?

States a specific verb and resource ('Select nodes in the Figma editor') plus the secondary effect ('scroll them into view'). It is clearly distinguishable from the read-side sibling figma_get_selection, and the 'only way to move the user's cursor' line pins down its unique role.

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?

Gives an explicit use case — handing work over to the user ('look at what I just built') rather than making them hunt on a large canvas — which is actionable guidance for an agent deciding whether to call it. It lacks an explicit when-not/alternative clause, though 'Editor state only; the document is not modified' implicitly steers document edits elsewhere.

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