Skip to main content
Glama

performance_start_trace

Starts a performance trace on a target webpage to diagnose frontend issues and Core Web Vitals, helping improve page load speed.

Instructions

Start a performance trace on the target webpage. Use to find frontend performance issues, Core Web Vitals (LCP, INP, CLS), and improve page load speed.

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": {
      "pageId": "<pageId>"
    },
    "name": "performance_start_trace"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageIdYesTargets a specific page by ID.
reloadNoDetermines if, once tracing has started, the target page should be automatically reloaded. Navigate the page to the right URL using the navigate_page tool BEFORE starting the trace if reload or autoStop is set to true.
autoStopNoDetermines if the trace recording should be automatically stopped.
filePathNoThe absolute file path, or a file path relative to the current working directory, to save the raw trace data. For example, trace.json.gz (compressed) or trace.json (uncompressed).
ignoreCacheNoWhether to bypass the HTTP cache when reloading the page, to measure a cold page load. Only applies if reload is true. Active network mocks always disable the page HTTP cache.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior3/5

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

The annotations declare readOnlyHint=false, so the agent knows this is a stateful operation; the description does nothing to contradict that but also adds no behavioral context. It omits the important operational facts that a trace must be stopped (performance_stop_trace) before results can be analyzed, and that tracing has runtime overhead. Those gaps live in the schema's reload/autoStop notes rather than the description.

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?

Two short sentences, purpose first, intent second, with zero filler or redundant restatement of the 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?

For a five-parameter tool with no output schema and full schema-level parameter documentation, the description covers what the tool does and why. The main residual gap is the trace lifecycle (start-to-stop-to-analyze sequencing), which an agent must infer from the sibling name.

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 description coverage is 100%, so all five parameters (pageId, reload, autoStop, filePath, ignoreCache) are documented in the input schema, which sets the baseline at 3. The description adds the diagnostic purpose that explains why filePath output and cold-load measurement matter, though it adds no parameter-level detail itself.

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 gives a specific verb and resource ("Start a performance trace on the target webpage") and adds the diagnostic intent (frontend performance, Core Web Vitals LCP/INP/CLS). It implicitly pairs with performance_stop_trace via "start" but never names that 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?

It states a use case ("Use to find frontend performance issues... and improve page load speed"), which gives an agent a reason to select it. However, it offers no when-not conditions, no mention of the mandatory stop/analyze follow-up, and no contrast with adjacent tools like lighthouse_audit or performance_analyze_insight.

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