Skip to main content
Glama

fail_endpoint

Force one endpoint to fail in a simulated app while the rest keeps working, using offline, timeout, HTTP status, or delay settings to test error handling.

Instructions

Make requests to one endpoint fail inside a simulator app while the rest of the app works.

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>",
      "simulator": "<simulator>",
      "pattern": "<pattern>",
      "kind": "<kind>"
    },
    "name": "fail_endpoint"
  }
}

Input Schema

NameRequiredDescriptionDefault
appYesThe app: a bundle ID like com.me.MyApp, an app name, or * for every app in a simulator.
kindYesoffline: fails as no internet. timeout: times out. status: answers with an HTTP status. delay: sent after a wait.
valueNoFor status: the HTTP status (default 500). For delay: seconds (default 3). For timeout: at most this many seconds.
patternYesRequests whose URL contains this, like api.me.com/v1/feed. Use * for any text.
simulatorYesFor iOS Simulator apps: booted, any, a device name or a UDID. Leave out for a Mac app.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
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 it does disclose the most important trait: the failure is scoped to one URL pattern, not the whole app. It says nothing about whether the rule persists across app relaunches, whether it applies to a running app immediately, how it is removed, or whether permissions/simulator state are required.

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?

A single sentence with the action and the scoping constraint front-loaded; nothing is redundant or padded.

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?

Given five well-described parameters and no output schema, the description covers what the tool does and its key scoping behavior. The remaining gap is lifecycle information (persistence and how the injected failure is cleared), which an agent would want for a state-changing tool with no annotations.

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% and every parameter, including the kind enum and its value semantics, is already documented in the schema. The description adds no format, default, or interaction detail beyond that, so the baseline 3 applies.

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?

States a specific verb ('Make requests ... fail') plus the resource ('one endpoint') and the scoping condition ('inside a simulator app while the rest of the app works'). That scope statement distinguishes it from a blanket network tool, though it never names the siblings (mock_endpoint, set_network) it differs from.

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?

Usage is only implied: the 'one endpoint fails while the rest works' phrasing suggests fault injection for targeted testing, and contrasts implicitly with whole-simulator network tools. There is no explicit when-to-use, when-not-to-use, or named alternative such as mock_endpoint or clear_endpoints for undoing the fault.

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