Skip to main content
Glama
Sign In
Swipium

Swipium

by GeroPalombo
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

First run: plan or continue through login/onboarding

qa_first_run

Classify first-run screens and plan or continue through login, OTP, onboarding, permissions, or paywall gates using bounded, safe steps.

Instructions

Get past a first-run gate (login, sign-up, OTP, onboarding, permissions, paywall). mode:"plan" (default, read-only) classifies the screen and returns a safe plan. mode:"continue" runs bounded steps: generated data only in test/staging, never purchases, one needs_input question on OTP. Needs a prepared device.

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": {
      "sessionId": "<sessionId>"
    },
    "name": "qa_first_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNo
untilNocontinue: one_step (default) | until_gate (paywall/OTP/permission) | until_home.
maxStepsNocontinue: step cap.
sessionIdYes
maxDurationMsNocontinue: time cap in ms.
testDataPolicyPathNoTest-data policy JSON (default .swipium/test-data-policy.json).
allowGeneratedAccountNoOverride the policy on creating a throwaway account.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior3/5

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

Annotations declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the safety frame is already partly given; the description usefully adds that plan mode is read-only and that continue mode is bounded with no purchases allowed. It does not say what happens on a mid-run failure, how state is left behind, or what 'a safe plan' actually contains.

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

Conciseness4/5

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

Front-loaded and dense: the gate scope comes first, then the two modes, then the safety constraints. A few phrases are terse to the point of being cryptic ('one needs_input question on OTP', 'returns a safe plan'), which costs a perfect score.

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?

With no output schema and 7 parameters, the description does a reasonable job covering scope, modes, safety limits and the prepared-device prerequisite. Its main gap is the return value: an agent still does not know the shape of the plan or the step results it will receive.

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 coverage is 71% and the enum/description fields already document until, maxSteps, maxDurationMs and the policy path. The description adds real meaning for mode ('plan' is default and read-only; 'continue' executes steps), but says nothing about allowGeneratedAccount or testDataPolicyPath beyond what the schema states.

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 concrete verb-and-resource ('Get past a first-run gate') and enumerates the gate types it covers (login, sign-up, OTP, onboarding, permissions, paywall). The plan/continue split makes its scope distinguishable from a generic flow runner without the agent opening the schema.

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

Usage Guidelines4/5

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

Gives clear mode-selection guidance: mode:plan is the default and read-only, mode:continue runs bounded steps with explicit limits (generated data only in test/staging, never purchases, one needs_input question on OTP). It also states the prerequisite ('Needs a prepared device'), but never names a sibling such as qa_continue_from_blocker or qa_flow_run as the alternative when the first-run gate has already been passed.

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