Skip to main content
Glama
Mac Health MCP

Mac Health MCP

Why is my Mac slow?

diagnose_slowness
Read-onlyIdempotent

Identifies why a Mac feels slow by checking uptime, memory, disk, CPU, heat, and startup items, then ranks likely causes with numbers and fixes.

Instructions

Finds the likely reasons why this Mac feels slow and ranks them, most likely first. Checks uptime (over 14 days), memory pressure and swap (over 2 GB, naming the apps using most memory), free disk (under 10 %, naming the largest home folders), single processes over 80 % CPU in two measurements (named and explained), Spotlight indexing, heat throttling (kernel_task) battery health (under 80 %) and startup items (15 or more from third parties, at most three names shown). Each cause has a plain-Swedish explanation, the number behind it and what the user can do. Use it first when the user asks why their Mac is slow. Takes a few seconds (longer only if the disk is nearly full). Read-only, local.

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": "diagnose_slowness"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations (readOnly, idempotent, local, closed-world), the description discloses concrete evaluation thresholds (14-day uptime, 2 GB swap, under 10% disk, 80% CPU in two measurements, battery under 80%, 15+ startup items), how many names are surfaced, that it takes a few seconds with a slower path on full disks, and that each finding carries an explanation, a number, and a remedy. That is unusually rich behavioral disclosure.

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?

Purpose and routing are front-loaded, and the long threshold enumeration is dense but each clause carries decision-relevant information. The check list runs as one long unpunctuated sentence ('...kernel_task) battery health...'), which costs a little readability but not meaning.

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?

There is no output schema, yet the description explains what comes back — ranked causes, each with a plain-Swedish explanation, the underlying number and a suggested action — plus runtime expectations. For a zero-parameter diagnostic tool this leaves no material gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so there is nothing to disambiguate; the 100% schema coverage baseline applies and no parameter meaning is missing.

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 opens with a specific verb and outcome — 'Finds the likely reasons why this Mac feels slow and ranks them' — and then enumerates the exact checks (uptime, memory pressure/swap, free disk, sustained CPU, Spotlight, kernel_task throttling, battery health, startup items). This makes it clearly the aggregate triage tool rather than a single-domain sibling like battery_report or disk_report.

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

Usage Guidelines4/5

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

'Use it first when the user asks why their Mac is slow' gives an explicit trigger and priority ordering, which is exactly the routing signal an agent needs. It does not name the individual report tools as follow-ups, so the when-not/alternatives half is only implied.

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