Skip to main content
Glama
escapeWu

chrome-agent-bridge

by escapeWu
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

Start network monitoring

browser_network_start

Start a metadata-only network monitor for a specific Chrome tab to capture request details without headers or bodies. Use rawSessionId to reuse an existing debugger attachment and avoid a second one.

Instructions

Start a tab-scoped, metadata-only Chrome network monitor. Pass rawSessionId to reuse that Raw CDP attachment instead of attaching a second debugger. Headers and bodies are never returned. Without rawSessionId the monitor holds the tab under an idle lease; always stop it.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tabIdYes
browserNoWhich connected Chrome to use: an instanceId or label from browser_list_instances. Required when more than one browser is connected; session-based tools infer it from their sessionId.
urlModeNoorigin_path
maxBytesNo
maxEventsNo
leaseTtlMsNoIdle period after which another task may take over the attachment (default 300000). Any valid call renews it.
ownerLabelNoDiagnostic label shown to other tasks that find the tab busy; not an identity.
urlIncludesNo
rawSessionIdNo
resourceTypesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.10.0
    • addedInput schema / properties / leaseTtlMs
      Added value: +{
+  "description": "Idle period after which another task may take over the attachment (default 300000). Any valid call renews it.",
+  "maximum": 3600000,
+  "minimum": 30000,
+  "type": "integer"
+}
    • addedInput schema / properties / ownerLabel
      Added value: +{
+  "description": "Diagnostic label shown to other tasks that find the tab busy; not an identity.",
+  "maxLength": 64,
+  "type": "string"
+}
  2. Changed1 schema field changedv0.9.1
    • addedInput schema / properties / browser
      Added value: +{
+  "description": "Which connected Chrome to use: an instanceId or label from browser_list_instances. Required when more than one browser is connected; session-based tools infer it from their sessionId.",
+  "maxLength": 100,
+  "minLength": 1,
+  "type": "string"
+}
  3. First observedv0.6.0

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the burden well: it discloses that this is metadata-only (headers/bodies never returned), that a rawSessionId lets you reuse an existing Raw CDP attachment instead of double-attaching, that a tab idle lease is acquired, and that the monitor must always be stopped. Missing: any note on rate limits, permissions, or the retention window of collected events.

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?

Three tightly-packed sentences, front-loaded with the core 'start a tab-scoped monitor' purpose, followed by the rawSessionId optimization and the resource-lifetime warning. 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 10-parameter tool with no annotations, no output schema, and 30% schema coverage, the description covers the key behavioral points (metadata-only, lease behavior, stop required) but is silent on the seven undocumented parameters and the lifecycle relationship with browser_network_stop. Slightly short of complete.

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 30%, so the schema leaves 7 of 10 parameters undocumented. The description only clarifies rawSessionId semantics; it does not explain urlMode, maxBytes, maxEvents, resourceTypes, urlIncludes, or the tabId/browser pairing. It partially compensates but leaves notable gaps.

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 a tab-scoped, metadata-only Chrome network monitor'). The 'tab-scoped' and 'metadata-only' qualifiers distinguish it precisely from siblings like network_intercept and browser_network_poll.

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 description implies usage via the rawSessionId reuse hint and the 'always stop it' directive, but never explicitly states when to choose this tool over siblings such as network_intercept, network_export_har, or browser_network_poll. There is no 'use this when...' guidance.

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