Skip to main content
Glama

Designesy

by io.github.LE-VAI

designesy_guardrails

Generate a frozen build-contract bundle for AI coding agents from any design system URL — the product layer. Ingests a site, extracts its :root tokens, and emits 6 outputs: (1) DTCG-format token file, (2) Stylelint config generated from token values, (3) AGENTS.md-format rules with token allowlist, (4) component contract with allowed prop patterns, (5) anti-pattern documentation, (6) DESIGN.md file (Google open spec, google-labs-code/design.md) — YAML front matter + markdown body, the de-facto AI-readable design-context standard. Use this when you need to turn a design system into the file AI agents read and the lint that enforces it. When NOT to use: for design-contract scoring, use designesy_score; for token-file validation, use designesy_tokens_score; for drift detection, use designesy_drift_score. Executable — fetches the URL, extracts CSS + :root custom properties, generates the bundle. No browser needed. Returns JSON: { ok, url, score (0-100, emission completeness), grade, pass, warn, fail, total, tokensExtracted, bundle: { tokens, lintConfig, agentRules, componentContract, antiPatterns, designMd }, checks[{id, item, category, status, detail}] }. Results cached ~24h per URL.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlNoURL to generate guardrails for. Defaults to https://www.designesy.org/ if not provided.

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations, the description carries full burden. It clearly discloses execution behavior ('fetches the URL, extracts CSS + :root custom properties'), notes 'No browser needed', and describes the return JSON structure plus caching behavior. It does not mention auth or rate limits, but covers key operational traits.

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?

The description is long but every sentence earns its place: it lists outputs, gives usage guidance, explains behavior, and specifies the return format. It is front-loaded with the core purpose and structured with numbered lists and clear sections, making it easy to parse.

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?

Given the tool's complexity (six outputs, checks array, no output schema), the description is remarkably complete. It enumerates all bundle components, defines the JSON response fields, and notes the 24-hour cache — enough for an agent to invoke correctly without additional documentation.

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 coverage is 100% and the schema already describes the url parameter with a default. The description reinforces the URL's role but adds no new parameter details beyond what the schema provides, so a baseline 3 is appropriate.

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 opens with 'Generate a frozen build-contract bundle for AI coding agents' — a specific verb, resource, and scope. It enumerates the six distinct outputs and explicitly differentiates from sibling tools by naming alternatives for scoring, validation, and drift detection.

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 directly states when to use ('Use this when you need to turn a design system into the file AI agents read and the lint that enforces it') and provides explicit when-not-to-use guidance with named alternatives: designesy_score, designesy_tokens_score, and designesy_drift_score.

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

All Designesy toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.7/5.0
Disambiguation5/5

Each tool has a clearly scoped purpose, and the extensive 'When NOT to use' notices cleanly separate the many scoring variants (e.g., score, drift, readiness, monitor, tokens, motion, a11y). Even similar informational endpoints (contract, skill, llms) are differentiated by format and use case. No two tools appear to do the same thing.

Naming Consistency5/5

All tools follow a consistent 'designesy_' prefix, and scoring tools uniformly append '_score' (e.g., drift_score, tokens_score, monitor_score). Non-score tools use descriptive noun suffixes (catalog, contract, report, guardrails). The pattern is predictable and uniform throughout.

Tool Count4/5

At 17 tools, the set is slightly above the ideal 3-15 range, but the breadth of the design-system intelligence domain justifies the count. Each scoring variant targets a different artifact (live URL, token file, Lottie, temporal drift) and the informational endpoints serve distinct formats. The tool count is heavy but not bloated.

Completeness5/5

The toolset covers the full assessment lifecycle: full audit (score), drift and temporal governance (drift_score, monitor_score), AI readiness (readiness_score), token and motion validation (tokens_score, motion_score), accessibility framework (a11y_score), diff (compare), composite report (report), guardrails generation, and multiple discovery formats (catalog, contract, skill_md, llms). No obvious dead ends exist; each tool leads to a usable artifact or clear next step.

Resources