Skip to main content
Glama
krusch-frontend-mcp

krusch-frontend-mcp

by kruschdev

ingest_figma_tokens

Idempotent

Parses Figma JSON token exports, converts them into CSS variables and Tailwind configs, and indexes the results in the RAG database for design-system retrieval.

Instructions

Parses Figma JSON token exports, converts them to CSS variables/Tailwind configs, and indexes them into the RAG database.

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": {
      "tokensJsonStr": "<tokensJsonStr>"
    },
    "name": "ingest_figma_tokens"
  }
}

Input Schema

NameRequiredDescriptionDefault
tokensJsonStrYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.1

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=true, and openWorldHint=false. The description adds genuinely new behavioral context: the tool has a persistent side effect — it indexes results into the RAG database. However, it says nothing about whether re-ingesting the same tokens overwrites or duplicates entries, what permissions or target database/workspace are needed, or what is returned on success or parse failure.

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?

A single front-loaded sentence with three parallel clauses, each carrying distinct information (input format, conversion targets, storage side effect). No filler, no redundancy, nothing an agent must read past to get the essentials.

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 one-parameter tool with no output schema, the definition covers input format, transformation, and the persistence side effect, so the core is covered. The gaps are the return value, error behavior, and identity/namespace for the RAG index, which matter for a mutating ingestion tool but are secondary given the annotations.

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?

Only one parameter, tokensJsonStr, and the schema provides zero description coverage for it. The description partially compensates by indicating the expected content ('Figma JSON token exports'), which tells the agent the string must be a JSON export rather than a file path or URL. It gives no detail on expected schema shape, encoding, or what a malformed payload does, so the compensation is only partial.

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?

Description uses three concrete verbs (parses, converts, indexes) on a specific resource (Figma JSON token exports) with named outputs (CSS variables/Tailwind configs, RAG database). This is far more informative than a tautology, but it never distinguishes itself from plausible siblings such as generate_css_variables_from_figma or css_to_tailwind, which sound like overlapping steps of this same pipeline.

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 statement, no prerequisites, no exclusions. An agent cannot tell whether to call this instead of, or in addition to, generate_css_variables_from_figma and css_to_tailwind for the same input. Usage is only inferable from the tool name and the listed side effects.

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