Skip to main content
Glama

network_session

Manage cookies, local/session storage, Playwright storageState files, and resource blocking presets to control browser sessions and reduce page load overhead.

Instructions

Manage browser cookies, localStorage/sessionStorage, Playwright storageState files, quick blocking presets (turbo, no-images, no-media, clean), and custom resource/URL blocking.

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": "network_session"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlsNo
itemsNo
tabIdNo
presetNoQuick resource/tracker blocking preset for faster page loads (clean unblocks all).
cookiesNo
blockUrlsNo
unblockAllNo
storageTypeNolocal
cookieActionNo
storageActionNo
blockResourcesNo
loadStorageStatePathNoLoad storageState from cwd or TURBO_BROWSER_SAVE_ROOT.
saveStorageStatePathNoSave storageState under cwd or TURBO_BROWSER_SAVE_ROOT.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.6.1
    • addedInput schema / properties / loadStorageStatePath / description
      Added value: +"Load storageState from cwd or TURBO_BROWSER_SAVE_ROOT."
    • addedInput schema / properties / saveStorageStatePath / description
      Added value: +"Save storageState under cwd or TURBO_BROWSER_SAVE_ROOT."
  2. First observedv0.4.0

TDQS

C2.6/5.0
Behavior2/5

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

Annotations already state readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=true, so the safety bar is lower, yet the description adds nothing beyond that. It does not say that cookie/storage 'clear' actions destroy state, that presets persist across calls (non-idempotent), whether paths are read or written relative to a save root, or what any call returns.

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

Conciseness3/5

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

It is a single efficient sentence with no filler, but it is a flat run-on enumeration that fails to group the five capability families or front-load the most common operations. Structuring it by operation group would cost no extra length and greatly aid scanning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 13 optional parameters, nested objects, no output schema, and low schema coverage, this is a complex tool that the one-line description cannot cover. Critical operational detail—which parameter combos constitute a valid cookie get versus clear versus block operation—is absent.

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

Parameters2/5

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

Schema description coverage is only 23% across 13 parameters, so the description must compensate and does not. It never explains urls, items, tabId, cookies, blockUrls, blockResources, unblockAll, storageType's default scope, or how cookieAction/storageAction pair with the cookies/items arrays.

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 enumerates concrete resource families: cookies, localStorage/sessionStorage, Playwright storageState files, blocking presets, and custom URL/resource blocking, so an agent can see the domain. The verb 'Manage' is generic and the tool is a multiplexer spanning five unrelated operations with no indication of how they relate, and no sibling differentiation is offered.

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

Usage Guidelines2/5

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

There is no statement of when to use this tool versus alternatives like capture_page or evaluate_js, no prerequisites, and no guidance on which parameter groups belong to which capability. The agent must infer usage entirely from the schema.

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