Skip to main content
Glama
tokensqueezer-mcp

tokensqueezer-mcp

get_figma_context

Retrieve current squeezed Figma design context and optional PNG preview in nine code formats, with adjustable compression levels for AI coding workflows.

Instructions

Get the current squeezed Figma design context + optional multimodal PNG preview. Supports 9 output formats and on-the-fly compression levels (full, compact, sparse).

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": "get_figma_context"
  }
}

Input Schema

NameRequiredDescriptionDefault
outputNoOutput format: jsx, shadcn, vue, svelte, md, html, tailwind, spec (DESIGN.md), or dtcg (W3C tokens.json). Defaults to md.
compressionNoOptional compression override: full (all classes), compact (fold repeated siblings, ideal for reasoning models), sparse (DOM skeleton + Vision).
include_metadataNoInclude layer name, token counts, and savings metadata. Defaults to true.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.4.1

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations, the description carries the full burden. It usefully discloses compression behavior ('on-the-fly', full/compact/sparse) and that output can include a multimodal PNG preview, but it omits what 'squeezed' actually means, whether a Figma connection/selection is required, and how the PNG preview is triggered when no schema parameter controls it.

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?

Two sentences, front-loaded with the core action and no wasted words. Minor deductions for unexplained jargon ('squeezed') and for advertising a PNG preview that has no corresponding parameter.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

All parameters are optional, the schema fully documents them, and annotations are absent but the tool is a read operation. The description covers what is returned at a high level and the compression options. The only minor gap is the unexplained 'squeezed' term and how the PNG preview is controlled, which prevents a perfect score.

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 the schema already documents all three parameters including enum meanings. The description only restates the compression level names, adding no syntax, defaults, or interaction details beyond the schema — the baseline 3 applies.

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: 'Get the current ... Figma design context'. The added detail about 9 output formats and compression levels distinguishes it reasonably from siblings like get_design_spec and get_design_tokens, though it never explicitly contrasts with them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use or when-not-to-use guidance is given. The description lists capabilities (formats, compression) but never says which situations call for this tool over get_design_spec or get_design_tokens, leaving the agent to infer selection from the enum values alone.

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