Skip to main content
Glama

Better Design

by io.github.marvkr
OverviewDiscussionsAdmin

Create a New Design System

create-design-system

Starts generating a custom design system from a description of the product and its look, and returns the project id and project URL at once. Generation runs in the background and typically takes 1 to 3 minutes. get-design-system-status reports progress and returns the install command when it finishes. baseDesignSystemId starts from a catalog system the user picked, userConfirmedCustom records that the user chose fully custom, and brandCss builds from an existing brand token sheet, such as the output of extract-design-system. With none of the three, it generates nothing and returns the top catalog matches to show the user. Each call uses one credit from the user's Better Design account. Anyone with the registry or preview URL can view the generated source and previews.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
promptYesDescribe the design system the user wants. E.g. 'A warm, minimal design system for a personal finance app, soft pastels, rounded corners' or 'A brutalist developer tool aesthetic with sharp edges and monospace type'.
brandCssNoOptional. The user's extracted brand token sheet, verbatim: the fenced css block from extract-design-system / extract-from-url (`:root { --background: ...; }` plus optional `.dark { ... }`). When set, generation builds FROM this brand instead of a catalog look-alike, and baseDesignSystemId is ignored (a catalog base would leak its identity past the brand tokens).
baseDesignSystemIdNoOptional. The catalog id the USER picked from the `find-design-system` matches you showed them, used to bias generation toward that aesthetic (e.g. a theme tweak on top of Linear). Leave empty only when the user chose fully custom.
userConfirmedCustomNoSet true only when the user saw the find-design-system matches and chose fully custom. Without it, baseDesignSystemId or brandCss, the tool returns the matches and generates nothing.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, idempotentHint=false, openWorldHint=true, destructiveHint=false), the description discloses asynchronous background generation taking 1–3 minutes, a per-call credit cost, the no-op fallback behavior, and that anyone holding the registry/preview URL can view generated source and previews. These are non-obvious operational and privacy traits the schema and annotations cannot convey.

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?

Purpose and immediate output are front-loaded in the first sentence, followed by async timing, the follow-up tool, per-parameter semantics, cost, and visibility. Every sentence carries distinct information with no filler or repetition.

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?

No output schema exists, yet the description covers return values (project id + URL), async behavior, the status-check follow-up, all four parameters' interactions, cost, and the degenerate no-op path. An agent has everything required to invoke and follow up correctly.

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 description coverage is already 100%, so the baseline is 3; the description adds genuine meaning on top by defining the mutual-exclusion rule (brandCss overrides/ignores baseDesignSystemId and why) and the semantics of the no-parameter case. It stops short of exhaustively restating each field, which the schema already covers.

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?

The description gives a specific verb and resource ('Starts generating a custom design system from a description of the product and its look') and states the immediate return ('project id and project URL'). It also implicitly separates itself from find-design-system (which returns matches) and get-design-system-status (which reports progress), so an agent can route correctly without opening schemas.

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

Usage Guidelines5/5

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

It explicitly names the alternative tool (get-design-system-status) for the follow-up step and spells out the negative case: 'With none of the three, it generates nothing and returns the top catalog matches to show the user.' Each of the three conditional parameters is tied to a concrete user-selection scenario, which is exactly the when-to-use guidance needed.

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

All Better Design toolsInspect
Try in Browser
Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources