Skip to main content
Glama
krusch-frontend-mcp

krusch-frontend-mcp

by kruschdev

generate_component_styles

Read-onlyIdempotent

Generates CSS custom properties and classes from natural-language component descriptions, enriching output with retrieved design rules for consistent frontend styling.

Instructions

Given a component description (e.g. 'glassmorphism card with hover lift'), generates CSS custom properties and classes. Enriches output with RAG-retrieved design rules.

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": {
      "description": "<description>"
    },
    "name": "generate_component_styles"
  }
}

Input Schema

NameRequiredDescriptionDefault
paradigmNoOptional aesthetic paradigm to filter RAG rules by (e.g. 'refactoring-ui', 'universal', 'vercel')
descriptionYesNatural language description of the component aesthetic

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.1

TDQS

B3.3/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds real behavioral context by disclosing that output is enriched with RAG-retrieved design rules, implying a retrieval dependency and variable output content. It stops short of saying whether pre-ingestion is required or how output differs when no rules match.

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 core action and an inline example, with zero redundant phrasing. Every sentence contributes: one defines the action, one defines the enrichment behavior.

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

Completeness3/5

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

With no output schema, the description must carry the return-value burden, and it only loosely indicates format ('CSS custom properties and classes') without saying whether that is a string, an object, or files. For a low-complexity read-only generator it is roughly adequate, but the RAG dependency and output shape are under-specified.

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 both parameters are already documented, making 3 the baseline. The description adds a concrete example of the 'description' value, which helps an agent phrase input, but says nothing extra about 'paradigm' beyond what the schema's 'filter RAG rules by' already conveys.

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 concrete verb and resource ('generates CSS custom properties and classes') and anchors it with a realistic input example ('glassmorphism card with hover lift'). The 'given a component description' framing implicitly separates it from the Figma-token siblings, but no sibling is named explicitly, so differentiation is inferential rather than stated.

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?

There is no when-to-use or when-not-to-use guidance. An agent cannot tell from the text whether to call this, generate_css_variables_from_figma, or query_design_rules first, nor whether design rules must already be ingested before calling. The only hint is the schema's 'paradigm' parameter filtering RAG rules.

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