Skip to main content
Glama
Agency MCP Server

Agency MCP Server

Core Web Vitals

core_web_vitals
Read-only

Fetch real-user LCP, INP, and CLS p75 field data from Google's PageSpeed Insights when available, plus one Lighthouse lab run, to audit a client page’s performance.

Instructions

Core Web Vitals from Google's PageSpeed Insights API: real-user field data (LCP, INP, CLS at p75) when Google has it, plus one Lighthouse lab run.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "client": "<client>",
      "url": "<url>"
    },
    "name": "core_web_vitals"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesAbsolute URL inside the client's allowlist.
clientYesClient id from the server's config (dental, cafe, plumber).
strategyNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true, so the safety profile is covered. The description adds genuine context beyond that: this hits an external Google API, field data is only present 'when Google has it' (a conditional/partial-result case), and only a single Lighthouse run is performed. It does not disclose latency, rate limits, or what happens when field data is absent.

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?

A single dense sentence that front-loads the resource and source, with no filler. It is tight, though the 'plus one Lighthouse lab run' clause is slightly compressed and could be clearer about being a secondary artifact.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description usefully states the return payload (three named metrics at p75 plus a lab run), which is what an agent needs to trust the result. Gaps remain around the undocumented strategy parameter, external-API failure modes, and allowlist enforcement before invocation.

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 67% — url and client are documented in the schema, but strategy (the only enum) has no description there or in the prose. The description adds nothing about which strategy is default or how mobile vs. desktop affects results. Baseline 3 is appropriate since the schema carries most of the load but the enum parameter remains semantically undefined.

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?

The description names a specific resource (Core Web Vitals) and the source (Google's PageSpeed Insights API), and enumerates the exact metrics returned (LCP, INP, CLS at p75) plus a Lighthouse lab run. It implicitly separates itself from the Lighthouse-oriented sibling audit_page by labeling the lab portion as only 'one' run secondary to field data, though it never names a sibling explicitly.

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?

Usage is only implied: the mention of field vs. lab data signals this is the tool for real-user performance measurement. There is no explicit 'use this instead of audit_page when…' routing, no stated prerequisite that the URL must be in the client allowlist before calling, and no guidance on choosing a strategy.

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