Skip to main content
Glama
Electron Debug MCP Server

Electron Debug MCP Server

by amafjarkasi

perf_snapshot

Captures a composite performance profile by coordinating tracing, CPU profiling, and coverage, optionally reloading the page or recording an interaction, then bundles metrics and artifact URIs.

Instructions

Composite performance profiler: coordinates start_tracing + start_cpu_profile + start_coverage, optionally captures an interaction or reload, stops all collectors, and bundles perf audit, metrics, and artifact URIs.

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_snapshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
reloadNoIf true, reloads the current page during trace capture
targetIdNo
processIdNoProcess ID. If omitted, uses the single running app.
durationMsNoCapture window duration in milliseconds (default: 1000)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.15.1

TDQS

A4/5.0
Behavior3/5

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

The single annotation destructiveHint=false already says this is non-destructive. The description adds useful lifecycle detail: the tool starts three collectors, optionally reloads, stops everything, and returns artifacts. It does not cover failure modes, runtime cost, or what happens to previously running collectors, but it does cover the start/stop sequence that the annotation cannot express.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is one dense sentence, with the composite orchestration stated first and the returned artifacts stated last. No filler or repetition of the tool name.

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?

There is no output schema, so the description must carry the burden of explaining what comes back, and it does name the perf audit, metrics, and artifact URIs. Four optional parameters and a one-minute capture cap are left to the schema; the only gap is that the description mentions capturing an interaction that no parameter controls.

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?

Schema coverage is 75%, so detail is not required. The description notes the optional reload and interaction capture, but the interaction part has no matching parameter, which is a small mismatch. targetId, processId, and durationMs are handled by the schema and are not restated, which is acceptable.

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?

Names a concrete composite behavior: coordinates start_tracing, start_cpu_profile, and start_coverage, stops all collectors, and bundles perf audit, metrics, and artifact URIs. This clearly distinguishes it from the sibling single-collector tools without the reader needing to open a 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?

The word 'composite' and the list of collected data imply that this tool is used when an agent wants all profiling data in one call rather than calling the individual starters. However, there is no explicit when-to-use or when-not statement and no comparison against perf_audit or the single-purpose starters.

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