Lighthouse Audit

Run Lighthouse audit

run_lighthouse

Read-only

Run a Google PageSpeed Insights audit for a single public URL to get performance, accessibility, best-practice, and SEO scores plus diagnostic findings; choose mobile or desktop.

Instructions

Run a fresh Lighthouse lab audit of one public HTTP(S) page using Google PageSpeed Insights. Use for website speed and performance testing, accessibility checks, and basic on-page SEO checks. Returns performance, accessibility, best-practices and SEO scores, lab metrics, and audit findings. Defaults to mobile and can take up to about a minute. The URL is sent to Google. No separate signup or user-provided API key is required. Private or authenticated pages and whole-site crawls are unsupported. No audit history is retained.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`url`	Yes	Absolute public http:// or https:// URL of one page, at most 2,048 characters. Add https:// to a bare domain.
`device`	No	Device profile to emulate. One call audits one device; defaults to mobile.	mobile

Output Schema

TableJSON Schema

Name	Required	Description	Default
`ok`	Yes
`error`	Yes
`report`	Yes
`requestId`	Yes
`schemaVersion`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 2, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already cover read-only/open-world/idempotency, but the description adds several traits beyond them: default mobile profile, ~1 minute latency, URL is transmitted to Google, no signup or user API key needed, and no audit history is retained. These are exactly the side-effect and data-handling facts an agent needs.

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?

Front-loaded with purpose, then use cases, constraints, and behavior in tight sentences. The return-summary sentence is mildly redundant given the output schema exists, but overall it is dense and wastes little.

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?

With an output schema present, return values need not be explained; the description still covers latency, privacy/data-sharing, setup requirements, and hard limits. Nothing needed to call this correctly is missing.

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 both parameters are already documented. The description restates the mobile default and the one-page limitation but adds no format or syntax detail beyond what the schema provides; baseline 3 applies.

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 (run) and resource (Lighthouse lab audit) with precise scope: one public HTTP(S) page via Google PageSpeed Insights. No sibling tools exist, so no differentiation is needed; the purpose is unmistakable.

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?

Explicitly names the use cases (speed/performance testing, accessibility, on-page SEO) and the exclusions (private or authenticated pages, whole-site crawls). An agent can decide fit without inference.

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

Deploy Server

Other Tools

run_lighthouseA