Skip to main content
Glama

set_network

Throttle or break one app's network by creating and enabling a targeted rule, with presets or exact bandwidth, latency, loss, and failure-mode settings.

Instructions

Slow down or break one app's network, and only that app's. Creates the rule if needed and turns it on. Combine a preset with exact values or a failure mode.

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": {
      "app": "<app>"
    },
    "name": "set_network"
  }
}

Input Schema

NameRequiredDescriptionDefault
upNoUpload bandwidth in kilobits per second.
appYesThe app: a bundle ID like com.me.MyApp, an app name, or * for every app in a simulator.
downNoDownload bandwidth in kilobits per second.
lossNoPacket loss percent, 0 to 100.
afterNoFor drop: seconds before a connection is cut.
hostsNoComma-separated hosts to limit the rule to, like api.me.com,*.cdn.me.com.
jitterNoLatency variation in milliseconds.
onlineNoFor outages: seconds online.
presetNoNo Throttling, Edge, 3G, DSL, LTE, WiFi, Very Bad Network, 100% Loss, or a saved preset.
failureNoairplane: every connection fails at once. refuse: refuse a percent of new connections. timeout: connections never answer. drop: cut connections after some seconds. outages: go offline and back repeatedly.
latencyNoAdded latency in milliseconds.
offlineNoFor outages: seconds offline.
percentNoFor refuse: the percent of connections refused.
simulatorNoFor iOS Simulator apps: booted, any, a device name or a UDID. Leave out for a Mac app.
hosts_modeNoonly (default): just those hosts; except: everything but them.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations, the description carries the full burden and delivers two useful behavioral facts: the rule is created if absent and then enabled, and the effect is confined to a single app. It omits permissions or privilege requirements, whether existing connections are immediately affected, and whether the rule persists until reset.

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 short sentences, front-loaded with the scoping constraint that matters most, and no filler for a tool with 15 parameters. Every clause carries information.

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

Completeness3/5

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

For a 15-parameter mutation tool with no annotations and no output schema, the description covers the core intent and the create-and-enable behavior but leaves out what the call returns, how the effect is undone, and any target prerequisites. Adequate, not 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 100%, so units, enum meanings, and the hosts_mode default are already documented. The description's "combine a preset with exact values or a failure mode" adds genuine interaction semantics that the schema does not express, but the remaining 15 parameters get nothing further.

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?

"Slow down or break one app's network, and only that app's" gives a concrete verb pair (throttle/sever) plus the resource and its scope, so an agent can tell this is a per-app network-conditioning tool rather than a global one. It stops short of naming any sibling (reset_network, fail_endpoint) to sharpen the boundary.

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?

"Combine a preset with exact values or a failure mode" tells the agent how the three parameter families relate, which is real usage guidance. It never states when to pick this over reset_network or fail_endpoint, nor any precondition such as simulator versus Mac app.

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