Skip to main content
Glama

Create design system

kaava_create_system
DestructiveIdempotent

Generate a complete, contrast-checked design system from a brand color and optional style, save it as kaava.json, and return a summary and contrast report for token emission.

Instructions

Generate a complete design system from a short brief and save it as kaava.json in the project root. Only brandColor is required; style picks a hand-authored character for the rest (read kaava://styles for what each one is). Returns a summary and a contrast report. Follow with kaava_emit to write tokens for the project stack.

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": {
      "brandColor": "<brandColor>"
    },
    "name": "kaava_create_system"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoName of the design system or product.
fontsNoFont families. A single name ("Inter") gets a system fallback stack appended; a comma-separated value is used as the full stack. `display` is for headings and defaults to `sans`.
styleNoA hand-authored style that decides the character of the system: ramp shape, typography, spacing rhythm, corners, elevation, motion. The fields below override single aspects of it; leave them out to keep the style as designed.
accentNoSecondary accent color (CSS color). Omit to derive one from the brand hue according to the style.
dryRunNoReturn the content that would be written instead of writing files.
radiusNoReplace the style's corner rounding with a generic scale. "full" gives pill-shaped controls.
densityNoControl sizes and spacing rhythm. Default: the density the style was designed for.
shadowsNoReplace the style's shadows with a generic recipe, or "none" for a flat system.
darkModeNoGenerate a dark theme. Default true.
overwriteNoReplace an existing kaava.json. Without this, an existing system is left untouched.
typeScaleNoReplace the style's type sizes with a modular scale of this ratio. 1.125 = tight/dense UI, 1.2 = balanced, 1.333 = expressive/editorial.
brandColorYesPrimary brand color in any CSS syntax: "#4f46e5", "rgb(79 70 229)", "oklch(0.55 0.2 270)", "rebeccapurple".
descriptionNoOne or two sentences on what the product is and who it is for.
neutralTintNoHow much of the brand hue tints the greys. 0 = pure grey, 1 = clearly tinted.
projectRootNoAbsolute path of the project. Defaults to the first workspace root the client exposes, else the server working directory.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and idempotentHint=true, and the description adds the specific mechanics: it writes kaava.json into the project root, overwrite replaces an existing file while omitting it leaves the existing system untouched, and dryRun returns content instead of writing. That is meaningful disclosure beyond the annotations, though the practical consequences of destructive writes (e.g. what is lost on overwrite) could be stated more sharply.

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?

Four short sentences, front-loaded with the core action and artifact, then the minimum input, then the return values, then the follow-up. No sentence restates another or wastes tokens.

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 15-parameter tool with no output schema, the description covers the write target, the overwrite and dryRun behaviors, and the return shape ("a summary and a contrast report"). It omits any mention of the kaava_audit or kaava_check_contrast siblings for validating the generated system, which would round it out.

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 15 parameters in depth. The description adds only the required-parameter and style-override framing plus a pointer to the kaava://styles resource, which is useful but modest against an already rich schema.

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?

"Generate a complete design system from a short brief and save it as kaava.json in the project root" gives a specific verb, resource, and concrete artifact. It also distinguishes itself from the sibling that follows it ("Follow with kaava_emit to write tokens for the project stack"), so an agent knows this tool produces the system, not the stack tokens.

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 entry condition (only brandColor required; everything else derives from style) and the follow-up step with kaava_emit. It does not explicitly contrast with kaava_update_system, so an agent must infer when to create versus update, which keeps this below a 5.

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