Skip to main content
Glama

browser_network_start

Starts capturing HTTP requests, responses, failures, and WebSocket messages on a browser tab so you can inspect network activity; reload afterward to include initial page loading.

Instructions

Start network capture on a tab. Captures future HTTP requests, responses, failures and WebSocket messages. Reload the page afterwards to capture initial loading. Starting an already active capture preserves it; starting a stopped capture resets its buffer.

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": "browser_network_start"
  }
}

Input Schema

NameRequiredDescriptionDefault
tabIdNoTab to capture or inspect (active tab by default).
maxEntriesNoMaximum retained requests (1000 by default). Oldest requests are evicted.
captureBodiesNoCollect response bodies (default: true). Text is capped at 262144 characters per response, with 8388608 characters shared by response bodies and WebSocket frames.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.0.0

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and mostly rises to it: it discloses that capture is forward-only, that restarting an active capture is a no-op preservation, and critically that restarting a stopped capture resets the buffer (a data-loss behavior an agent must know). Missing are auth/permission requirements or whether capture is tab-scoped only.

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?

Four short sentences, front-loaded with the action, then capability, then the reload tip, then the state-restart caveat. Every sentence carries distinct, actionable information with no filler.

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 no-annotation, no-output-schema, 3-optional-param capture tool, the description covers the important lifecycle semantics (forward-only capture, reload for initial load, restart behavior). It could still say that captured data is retrieved via browser_network_list/detail, which would close the loop for a new agent.

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 100%, so tabId, maxEntries and captureBodies are already fully documented in the schema, including defaults and eviction semantics. The description adds no parameter-level meaning beyond that, which is the baseline case rather than a deficiency.

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?

States a specific verb and resource: 'Start network capture on a tab.' The 'Start' verb implicitly contrasts with the sibling browser_network_stop, and the scope (captures HTTP requests, responses, failures, WebSocket messages) tells an agent exactly what data this produces versus browser_network_list or browser_network_detail.

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?

Gives concrete operational guidance: reload the page after starting to capture initial loading. That is a real when-to-use instruction an agent would otherwise get wrong. It lacks explicit exclusions or a pointer to browser_network_stop/browser_network_clear, so it stops short of a 5.

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