Skip to main content
Glama

read_network_requests

List recorded HTTP traffic for a tab to confirm API calls fired, inspect responses, or locate slow-loading assets, with method, status, type, time, bytes, and URL per request.

Instructions

List the HTTP traffic recorded for one tab - documents, scripts, stylesheets, images, XHR and fetch alike - as one padded row per request, oldest first, giving method, status, resource type, elapsed time, bytes transferred and URL, flagged when the request failed or is still in flight. Use it to confirm an API call actually fired, see what came back, or find the asset costing you seconds. Traffic to any host is kept, not only the page's own origin, but a tab's log is emptied as soon as that tab moves to a different origin (scheme, host or port), and only its 1000 most recent requests survive. Recording begins with your first call to this tool or read_console_messages, so a request made earlier than that does not exist here; reload and read again. tabId is required and has to be a tab in this session's group - tabs_context_mcp will give you one.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
clearNoSet true to discard this tab's recorded requests after the reply is built, so a later read starts from empty instead of repeating what you have already looked at. Defaults to false.
limitNoLargest number of matching requests to return, most recent kept; 100 unless you say otherwise. The header reports how many matches the cap hid, which is your cue to ask for more.
tabIdYesThe tab whose requests you want, as the numeric id from tabs_context_mcp. Traffic is buffered per tab, and only tabs belonging to this session can be read.
urlPatternNoA plain substring, matched case-insensitively against the whole URL: '/api/' isolates API traffic, 'fonts.' one host's assets. Literal text, not a regular expression - dots and slashes stand for themselves. Leave it off and every recorded request comes back.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A5/5.0
Behavior5/5

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

With no annotations, the description fully discloses side effects: the clear parameter discards recorded requests, recording begins on first call, only session tabs are readable, and only the most recent 1000 requests are kept. Also notes the header reporting hidden matches.

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 long but every sentence carries essential operational detail. It is well-structured, covering purpose, usage, and limitations without redundancy or filler.

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?

Given no output schema, the description explains the output format (rows with method, status, resource type, etc.) and the header behavior regarding capped matches. This gives the agent a clear picture of what to expect.

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

Parameters5/5

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

Every parameter is described in the schema, and the tool description adds context: tabId is linked to tabs_context_mcp, urlPattern is explicitly a literal substring (not a regex), and limit's behavior is clarified with the default and the header cue.

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 explicitly states it lists HTTP traffic for a tab, enumerating the types of resources and the fields per row. It clearly differentiates from siblings like read_page or read_console_messages by focusing on network requests.

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

Usage Guidelines5/5

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

Provides direct use cases: confirming an API call fired, inspecting responses, and finding slow assets. Also explains key limitations (per-tab session, recording start, buffer cap) which helps the agent decide when to use this tool.

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