Skip to main content
Glama

Lint CSS for Design Quality

lint_css

Lint pasted CSS or page URL to detect design-system issues—low contrast, missing focus outlines, tiny text, color/font overload, off-grid spacing, reduced-motion gaps, and token drift—and return a score.

Instructions

Lint CSS (pasted or from a URL) for design-system problems: low text contrast, removed focus outlines, tiny text, too many colors, font sizes or families, off-grid spacing, missing reduced-motion support, and colors that drift from your tokens. Returns a score. Deterministic, no API key needed.

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": "lint_css"
  }
}

Input Schema

NameRequiredDescriptionDefault
cssNoCSS text
urlNoPage URL to read stylesheets from
tokensNoOptional tokens JSON to check color drift against

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.6/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does real work: it discloses determinism, that no API key is required, that output includes a score, and it names the anonymous-free nature of the checks. It still omits what the findings actually look like (list of violations, severities, per-file grouping) and whether the call is read-only/non-mutating, which is a notable gap for a URL-fetching tool.

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?

Two sentences, front-loaded with the verb and the payoff. The long rule enumeration is dense but each item earns its place by scoping what is and isn't checked. Minor cost: the list reads as a run-on rather than a scannable structure.

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?

All three parameters are required=false, so the definition should state what happens with zero arguments and how css/url interact — it does not. No output schema exists, so the single word "Returns a score" under-describes an output that evidently includes per-issue findings. Adequate to call the tool, thin on how to interpret the result.

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 baseline is 3. The description adds mild value by clarifying that `css` is pasted text and `url` means stylesheets are fetched from a page, and by explaining that `tokens` is the drift baseline. It does not address whether `css` and `url` are mutually exclusive or can be combined, which is the one semantic question the schema leaves open.

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?

Specific verb plus resource ("Lint CSS") followed by a concrete enumerated rule set: contrast, focus outlines, tiny text, palette/type sprawl, off-grid spacing, reduced-motion, token drift. That is far more informative than a generic "check design quality," though it never distinguishes itself from overlapping siblings such as check_contrast or audit_accessibility.

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

Usage Guidelines3/5

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

Implied usage is clear — you have CSS or a page URL and want a rule-based design-system audit — and "pasted or from a URL" clarifies the two entry modes. However there is no explicit when-not guidance, no statement about how it differs from the contrast/accessibility auditors in the sibling set, and no note on whether to prefer this over analyze_design.

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