Skip to main content
Glama

Mimiq: test pages and copy on simulated people

by io.github.victorgulchenko
OverviewDiscussionsAdmin

mimiq.test_flow

Send simulated people through a multi-step flow (signup, onboarding, checkout) in a real browser, clicking and typing, to find the step where they get stuck or give up. Slower than test_page, and each person uses 30 credits. Returns each person's steps, where they stopped and why.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesWhere the flow starts. Must be publicly reachable. For localhost, open a cloudflared tunnel and pass the tunnel URL.
goalNoThe task each person tries, e.g. "complete the signup and reach the dashboard". Default: sign up and start using it.
countNoHow many simulated people (default 5, max 10; without a key a free flow has up to 3, and defaults to 3). Each runs a full browser session and uses 30 credits.
audienceNoWho the simulated people should be, in plain words, e.g. "startup founders in SF" or "parents shopping for kids toys". If omitted, Mimiq picks the likely audience from the content.
max_stepsNoMost steps per person (default 15).
timeout_secondsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / count / description
      Previous value: -"How many simulated people (default 5, max 10; without a key a free flow has up to 3, and defaults to 3). Each runs a full browser session and uses 10 credits."New value: +"How many simulated people (default 5, max 10; without a key a free flow has up to 3, and defaults to 3). Each runs a full browser session and uses 30 credits."
  2. Changed2 schema fields changed
    • changedInput schema / properties / count / description
      Previous value: -"How many simulated people (default 5, max 10). Each runs a full browser session and uses 10 credits."New value: +"How many simulated people (default 5, max 10; without a key a free flow has up to 3, and defaults to 3). Each runs a full browser session and uses 10 credits."
    • changedInput schema / properties / goal / description
      Previous value: -"What success looks like, e.g. \"complete the signup and reach the dashboard\"."New value: +"The task each person tries, e.g. \"complete the signup and reach the dashboard\". Default: sign up and start using it."
  3. Changed5 schema fields changed
    • changedInput schema / properties / audience / description
      Previous value: -"Who should test this page. Natural language, e.g. \"startup founders in SF\" or \"parents shopping for kids toys\". If omitted, Mimiq auto-detects the likely audience from page content."New value: +"Who the simulated people should be, in plain words, e.g. \"startup founders in SF\" or \"parents shopping for kids toys\". If omitted, Mimiq picks the likely audience from the content."
    • changedInput schema / properties / count / description
      Previous value: -"Number of simulated users (default 5, max 10). Each runs a full interactive browser session."New value: +"How many simulated people (default 5, max 10). Each runs a full browser session and uses 10 credits."
    • changedInput schema / properties / goal / description
      Previous value: -"What success looks like, e.g. \"complete the signup and reach the dashboard\". Providing a goal helps personas evaluate the page against a specific conversion objective."New value: +"What success looks like, e.g. \"complete the signup and reach the dashboard\"."
    • changedInput schema / properties / max_steps / description
      Previous value: -"Maximum navigation steps per persona (default 15)."New value: +"Most steps per person (default 15)."
    • changedInput schema / properties / url / description
      Previous value: -"Starting URL of the flow to test. For localhost, first create a cloudflared tunnel and pass the tunnel URL here."New value: +"Where the flow starts. Must be publicly reachable. For localhost, open a cloudflared tunnel and pass the tunnel URL."
  4. Changed6 schema fields changed
    • changedInput schema / properties / audience / description
      Previous value: -"Target audience description. E.g. \"small business owners looking for accounting software\"."New value: +"Who should test this page. Natural language, e.g. \"startup founders in SF\" or \"parents shopping for kids toys\". If omitted, Mimiq auto-detects the likely audience from page content."
    • addedInput schema / properties / audience / maxLength
      Added value: +500
    • removedInput schema / properties / bridge_id
      Removed value: -{
-  "description": "Deprecated. Use cloudflared tunnel directly instead.",
-  "type": "string"
-}
    • changedInput schema / properties / goal / description
      Previous value: -"What success looks like, e.g. \"complete the signup and reach the dashboard\"."New value: +"What success looks like, e.g. \"complete the signup and reach the dashboard\". Providing a goal helps personas evaluate the page against a specific conversion objective."
    • addedInput schema / properties / goal / maxLength
      Added value: +500
    • addedInput schema / properties / url / maxLength
      Added value: +2000
  5. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the annotations, the description discloses that this performs real browser interaction (clicking and typing), has a meaningful cost (30 credits per person), is slower than test_page, and returns per-step progress with stop reasons. This is substantial behavioral context that the annotations alone do not provide.

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 sentences deliver purpose, method, cost, performance comparison, and return value with no filler. The most important information is front-loaded, making it easy for an agent to quickly grasp the tool's role.

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 the rich schema and useful annotations, the description fills the remaining gaps: what the tool does, how it behaves, what it costs, and what it returns. A caller has enough information to select and invoke this tool appropriately.

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 83%, so the schema already documents most parameters well. The description adds some context around credit usage and the purpose of the flow, but it does not clarify individual parameters beyond what the schema already states. A baseline 3 is appropriate.

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 states a specific verb and resource: "Send simulated people through a multi-step flow" in a real browser to find where they get stuck or give up. This clearly distinguishes it from siblings like test_page and test_component by emphasizing multi-step journeys.

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?

The description gives clear context for when this tool applies: multi-step flows like signup or checkout in a real browser. It also provides a comparative signal by noting it is "Slower than test_page." It does not explicitly state exclusions or name all alternative tools, so it stops short of a 5.

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

All Mimiq: test pages and copy on simulated people toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources