Skip to main content
Glama

Mimiq: test pages and copy on simulated people

by io.github.victorgulchenko
OverviewDiscussionsAdmin

mimiq.test_copy

Read-only

Show one piece of copy (a headline, tagline, value proposition, email subject line or call to action) to simulated people and hear how they react and why. To choose between two versions, use mimiq.compare_copy. This tool still accepts variant_b and then runs that same comparison. Returns each person's reaction, objections and what would help, and the counts. With a key, the result ends with a link to the full report in the Mimiq app.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
countNoHow many simulated people (default 10, max 50).
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.
variant_aYesThe copy to test.
variant_bNoOptional second version. With it, this runs mimiq.compare_copy.
timeout_secondsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / variant_b / description
      Previous value: -"Optional second version. With it, this runs mimiq.compare_copy (needs a key)."New value: +"Optional second version. With it, this runs mimiq.compare_copy."
  2. Changed4 schema fields changed
    • changedInput schema / properties / audience / description
      Previous value: -"Target audience. E.g. \"developers evaluating CI/CD tools\". If omitted, defaults to \"likely audience for this 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: -"Simulated users per variant (default 10, max 50)."New value: +"How many simulated people (default 10, max 50)."
    • changedInput schema / properties / variant_a / description
      Previous value: -"The copy to test (or first variant for A/B comparison)."New value: +"The copy to test."
    • changedInput schema / properties / variant_b / description
      Previous value: -"Optional second variant for A/B comparison. If provided, returns a winner."New value: +"Optional second version. With it, this runs mimiq.compare_copy (needs a key)."
  3. Changed4 schema fields changed
    • changedInput schema / properties / audience / description
      Previous value: -"Target audience. E.g. \"developers evaluating CI/CD tools\" or \"e-commerce shoppers\"."New value: +"Target audience. E.g. \"developers evaluating CI/CD tools\". If omitted, defaults to \"likely audience for this content\"."
    • addedInput schema / properties / audience / maxLength
      Added value: +500
    • addedInput schema / properties / variant_a / maxLength
      Added value: +20000
    • addedInput schema / properties / variant_b / maxLength
      Added value: +20000
  4. First observed

TDQS

A4.1/5.0
Behavior4/5

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

The description reveals behavior beyond the annotations and schema: it returns each person's reaction, objections, helpful input, counts, and optionally a report link. It also clarifies that the people are simulated, which sets expectations about the tool's nature. Annotations already cover read-only safety, so the description does not need to repeat that.

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?

The description is front-loaded with the primary purpose and is generally tight. The only minor redundancy is the back-to-back explanation about variant_b and mimiq.compare_copy, but it does not seriously bloat the description.

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?

The description includes the tool's purpose, its sibling distinction, return contents, and the report-link behavior. Since there is no output schema, the explicit description of outputs is valuable. Parameter semantics are mostly handled by the input schema, so nothing critical is missing for an agent to invoke the tool effectively.

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 80% (only timeout_seconds lacks a description), so the schema carries most parameter meaning. The description adds context about copy types and clarifies that variant_b triggers a comparison, but much of the variant_b behavior is already stated in the schema. This is a passable baseline.

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 clearly states the verb and resource ('Show one piece of copy to simulated people') and gives concrete examples of what counts as copy. It also explicitly distinguishes itself from mimiq.compare_copy by naming the sibling and describing the single-version case.

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 an explicit usage directive: to compare two versions, use mimiq.compare_copy. It then notes that this tool still accepts variant_b and runs the same comparison, which slightly muddies the recommendation but still tells the agent the available options and their relationship.

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