Skip to main content
Glama
Electron Debug MCP Server

Electron Debug MCP Server

by amafjarkasi

perf_audit

Read-only

Collect Chrome performance metrics, navigation and paint timings, and recent audit issues from an Electron app. Use the results to identify performance bottlenecks without running a full Lighthouse report.

Instructions

Lighthouse-lite: Performance.getMetrics + nav/paint timing + recent Audits issues (not full Lighthouse)

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": "perf_audit"
  }
}

Input Schema

NameRequiredDescriptionDefault
targetIdNo
processIdNoProcess ID. If omitted, uses the single running app.
includeAuditsNo
includeNavTimingNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.15.1

TDQS

B3.3/5.0
Behavior3/5

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

readOnlyHint=true already tells the agent this is a safe read, so the description's extra value is in naming the underlying mechanisms (CDP Performance domain, nav/paint timing, audits issues) and capping expectations versus full Lighthouse. It does not disclose whether navigation timing requires a reload, whether the call is slow, or how the sections are combined.

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 compact line, front-loaded with the tool's identity and followed by the data sources and a scope caveat. Nothing is redundant, though the density of jargon like 'Lighthouse-lite' and 'Performance.getMetrics' makes it terse rather than maximally clear.

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

Completeness2/5

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

With no output schema, 25% parameter coverage, and four optional parameters, the description leaves an agent guessing at the shape of the result (metric names, units, whether audits are a summary or full list). For a diagnostic tool whose output is the whole point, this is a meaningful gap.

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 only 25%, with only processId documented, so the description has to compensate. It partially does: the mention of 'nav/paint timing' and 'recent Audits issues' maps to includeNavTiming and includeAudits. But targetId is unexplained in both places and no defaults or interaction between the flags is given.

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 the concrete data sources it gathers: CDP Performance.getMetrics, navigation/paint timing, and recent Audit issues. The parenthetical '(not full Lighthouse)' sets a clear scope boundary so an agent will not mistake it for a full Lighthouse run. It does not explicitly distinguish itself from the perf_snapshot or get_audit_issues siblings, keeping it below a 5.

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: an agent can infer this is the tool for a lightweight performance read, and '(not full Lighthouse)' acts as a partial when-not signal. There is no explicit statement of when to prefer this over perf_snapshot or get_audit_issues, and no prerequisites are stated.

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