Skip to main content
Glama

Update design system

kaava_update_system
Idempotent

Update an existing design system by patching brief fields or overriding individual tokens, then regenerate previously emitted files so CSS, Tailwind, SCSS, TypeScript, and design tokens stay in sync.

Instructions

Change the existing design system: patch brief fields (everything is re-derived) and/or override individual tokens. Files written earlier by kaava_emit are regenerated. Overrides are keyed by token path, e.g. {"radius.control": "{radius.full}", "dark:color.primary": "#8b9cff", "font.size.base": "1.0625rem"}; prefix semantic colors with "light:" or "dark:" to target one theme.

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": "kaava_update_system"
  }
}

Input Schema

NameRequiredDescriptionDefault
briefNoBrief fields to change. Omitted fields keep their current value.
dryRunNoReturn the content that would be written instead of writing files.
overridesNoToken overrides to add or replace: path -> CSS value or "{other.token}".
projectRootNoAbsolute path of the project. Defaults to the first workspace root the client exposes, else the server working directory.
removeOverridesNoOverride keys to remove, restoring the derived value.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already cover safety (idempotent, non-destructive, closed-world), so the description's value is in adding the side effect that previously emitted files are regenerated, and that partial brief patches re-derive dependent values. It still doesn't say what happens to overrides when a brief field that they derive from changes, or what a dryRun returns.

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?

Three sentences, front-loaded with the mutation scope before the regeneration warning and the override syntax. The inline examples are dense but earn their space by defining an otherwise ambiguous key format; only minor slack in the parenthetical 'everything is re-derived'.

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?

With no output schema and zero required parameters, the description supplies the operational context an agent needs to call this correctly. The remaining gap is the return value of a successful run or a dryRun, which neither schema nor annotations cover.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description goes beyond it by explaining override key syntax with concrete examples (token paths, alias references like '{radius.full}', and 'light:'/'dark:' theme prefixes) that the terse schema description does not convey. It adds no specifics for projectRoot or removeOverrides beyond the 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?

States a specific verb and resource ('Change the existing design system') and enumerates the two mutation modes (patching brief fields, overriding tokens). The phrase 'existing design system' plus the note about regenerating files from kaava_emit cleanly separates it from kaava_create_system and kaava_emit.

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?

Makes clear this is for modifying an already-created system and notes that patching brief fields causes everything to be re-derived, which is the key decision point between a brief patch and a token override. It does not explicitly say when to prefer kaava_create_system or kaava_get_tokens instead, nor when to use dryRun first.

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