Skip to main content
Glama

Audit Site

audit_site

Run an autonomous design audit on a live site or pasted CSS: extract the design language, lint quality, check contrast and color-blind risks, analyze type scale, and get a scored list of top fixes.

Instructions

An autonomous design audit of a live website (or pasted CSS) in one call: extracts the design language, lints quality, checks palette contrast, finds color-blind risks, analyzes the type scale, and ends with a scored list of the top fixes. 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": "audit_site"
  }
}

Input Schema

NameRequiredDescriptionDefault
cssNoCSS text to audit instead of a URL
urlNoPage URL (http or https)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose two useful traits: the run is deterministic and requires no API key. It also signals the aggregated, multi-stage nature of the operation. Missing for a network-touching mutation-free but slow/composite call: what happens when a URL is unreachable or is private, timeouts, whether fetches are logged, and which input wins if both url and css are supplied.

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?

The scope is front-loaded in the first clause and the trailing 'Deterministic, no API key needed' is a compact, high-value qualifier. The middle enumeration of six sub-analyses is long but each item conveys distinct capability, so little could be cut without losing routing information.

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?

For a high-complexity composite tool with no output schema and no annotations, the description covers the pipeline and hints at the return shape ('scored list of the top fixes'), which is more than most. Gaps remain around the zero-required-parameter case (neither url nor css supplied), failure modes for unreachable URLs, and roughly how much output to expect from a multi-check audit.

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% and the two parameters are self-documenting, so the baseline is 3. The description does reinforce that the tool accepts either a live site or pasted CSS, which helps an agent understand the two params are alternatives, but it adds no format, precedence, or size-limit guidance beyond what the schema already states.

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 names a specific verb and resource ('autonomous design audit of a live website or pasted CSS') and then enumerates exactly what the audit produces: design language extraction, quality linting, palette contrast, color-blind risks, type scale, and a scored fix list. An agent can tell this is the composite/orchestrator tool in a family of single-purpose siblings (lint_css, check_contrast, simulate_colorblind) without opening any schema.

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?

'In one call' implies this is the batch alternative to calling lint_css, check_contrast, simulate_colorblind and extract_tokens individually, which is genuine but implicit routing guidance. There is no explicit when-to-use/when-not statement, no stated preference for a single-purpose sibling when only one check is wanted, and no prerequisite notes about the target site being publicly reachable.

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