Mimiq: test pages and sign-up flows on simulated people

Test a page

mimiq.test_page

Starts immediately unless the recruited crowd is wrong (more than 1 in 5 not the requested audience) or the page could not be read to check its market; the result includes the audience summary, examples and fit. Only those return audience_review: show the warning, then use review_id, confirm_audience and audience_fit_acknowledged to continue, or audience_correction to recruit again. Show a web page to simulated people and hear how they react: who would stay, who would leave, and why. Each person scrolls the page and says what confused them, what they doubted and what would change their mind. Use it after you build or change a landing, pricing or signup page, then fix what they raised and test again. Needs a public URL (for localhost, open a tunnel first; see the server instructions). Returns each person's action, thoughts and objections, and the counts. With a key, the result ends with a link to the full report in the Mimiq app.

Input Schema

TableJSON Schema

Name	Required	Description
`url`	Yes	The page to test. Must be publicly reachable. For localhost, open a cloudflared tunnel and pass the tunnel URL.
`goal`	No	What the page should get people to do, e.g. "sign up for the waitlist".
`count`	No	How many simulated people (default 10, max 50). Each person uses one credit.
`audience`	No	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.
`review_id`	No	The review_id from a low-fit review or completed/running result. Bound to this URL and test kind.
`timeout_seconds`	No
`confirm_audience`	No	Start with the reviewed people after showing them to the user.
`audience_correction`	No	Not quite? Change who and rerun: use with review_id. Recruits a new crowd under the existing credit rules; starts unless the new crowd is wrong, otherwise returns a new review.
`audience_fit_acknowledged`	No	Set only after telling the user about an audience-fit warning and they choose to continue.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`run`	No
`call`	No
`tool`	Yes
`status`	No
`report_url`	No
`summary_card`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedSep 30, 2026

changedInput schema / properties / audience_correction / description

Previous value: -"Not quite? Change who and rerun: use with review_id. Recruits a new crowd under the existing credit rules; starts at 80% fit or more, otherwise returns a new review."New value: +"Not quite? Change who and rerun: use with review_id. Recruits a new crowd under the existing credit rules; starts unless the new crowd is wrong, otherwise returns a new review."

changedInput schema / properties / audience_fit_acknowledged / description

Previous value: -"Set only after telling the user about a below-80% fit warning and they choose to continue."New value: +"Set only after telling the user about an audience-fit warning and they choose to continue."

Changed1 schema field changedSep 30, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "call": {
+      "additionalProperties": true,
+      "properties": {
+        "headline": {
+          "type": "string"
+        },
+        "pick": {
+          "type": [
+            "string",
+            "null"
+          ]
+        },
+        "reason": {
+          "type": "string"
+        }
+      },
+      "type": "object"
+    },
+    "report_url": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "run": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "status": {
+      "type": "string"
+    },
+    "summary_card": {
+      "type": "string"
+    },
+    "tool": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "tool"
+  ],
+  "type": "object"
+}

Changed4 schema fields changedSep 30, 2026

addedInput schema / properties / audience_correction

Added value: +{
+  "description": "Not quite? Change who and rerun: use with review_id. Recruits a new crowd under the existing credit rules; starts at 80% fit or more, otherwise returns a new review.",
+  "maxLength": 1500,
+  "type": "string"
+}

addedInput schema / properties / audience_fit_acknowledged

Added value: +{
+  "description": "Set only after telling the user about a below-80% fit warning and they choose to continue.",
+  "type": "boolean"
+}

addedInput schema / properties / confirm_audience

Added value: +{
+  "description": "Start with the reviewed people after showing them to the user.",
+  "type": "boolean"
+}

addedInput schema / properties / review_id

Added value: +{
+  "description": "The review_id from a low-fit review or completed/running result. Bound to this URL and test kind.",
+  "maxLength": 100,
+  "type": "string"
+}

Changed4 schema fields changedSep 24, 2026

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 10, max 50). More = higher confidence but slower."New value: +"How many simulated people (default 10, max 50). Each person uses one credit."

changedInput schema / properties / goal / description

Previous value: -"What the page is trying to achieve, e.g. \"get visitors to sign up for the waitlist\". Providing a goal helps personas evaluate the page against a specific conversion objective."New value: +"What the page should get people to do, e.g. \"sign up for the waitlist\"."

changedInput schema / properties / url / description

Previous value: -"The URL to test. Must be publicly accessible. For localhost, first create a cloudflared tunnel and pass the tunnel URL here."New value: +"The page to test. Must be publicly reachable. For localhost, open a cloudflared tunnel and pass the tunnel URL."

Changed6 schema fields changedMar 17, 2026

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, auto-detects from page content."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 the page is trying to achieve, e.g. \"get visitors to sign up for the waitlist\"."New value: +"What the page is trying to achieve, e.g. \"get visitors to sign up for the waitlist\". 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
```

First observedMar 15, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false), it discloses non-obvious behavior: the run starts immediately unless the recruited crowd is >1 in 5 wrong, and only those runs return audience_review requiring an explicit confirm/correct step. Cost behavior (each simulated person consumes a credit) also appears. It stops short of stating runtime, auth requirements, or rate limits.

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?

The content is dense and mostly earns its place, but it is poorly ordered: the first sentence describes a rare exception branch before the tool's actual purpose, and the localhost/tunnel note is restated between description and schema. Front-loading is weak for a multi-sentence definition.

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?

For a 9-parameter, branching, open-world tool this covers the essentials: public-URL requirement, the tunnel workaround for localhost, credit cost, the audience-review path, and the returned actions/thoughts/objections counts. An output schema exists, so return-value detail is not required, and the description even points to the full report link when a key is present.

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

Parameters4/5

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

Schema coverage is 89%, so the schema already documents url, goal, count, audience, timeout and the review fields; baseline would be 3. The description adds real meaning by tying review_id, confirm_audience, audience_fit_acknowledged and audience_correction together as a conditional workflow (warn → confirm/continue → or correct and re-recruit), which the schema does not convey on its own.

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 states a specific verb+resource: "Show a web page to simulated people and hear how they react: who would stay, who would leave, and why," plus the concrete artifact it acts on (landing, pricing, signup pages). That clearly distinguishes it from a generic test tool, though it never names the sibling it is not (e.g. test_component/test_text/test_flow). The purpose is also undercut by being buried after the opening exception-branch sentence.

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?

"Use it after you build or change a landing, pricing or signup page, then fix what they raised and test again" gives explicit when-to-use timing and an iteration loop. It also spells out the audience-review continuation path (review_id, confirm_audience, audience_correction). It lacks any when-not-to-use or sibling routing guidance.

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 sign-up flows on simulated people tools Inspect

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.