QuestionPunk

Usability Walkthrough Start

usability_walkthrough_start

Idempotent

Run an AI walkthrough of an existing usability test: each persona tries each of its website tasks in a real headless browser, and each attempt is graded. Pass url to try the same tasks on a new deploy (the stored test keeps its own URL). Returns at once; poll usability_test_findings_get. The same clientRequestId returns the same walkthrough. Uses QuestionPunk AI credits.

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": {
      "surveyId": "<surveyId>",
      "questionId": "<questionId>",
      "clientRequestId": "<clientRequestId>"
    },
    "name": "usability_walkthrough_start"
  }
}

Input Schema

Name	Required	Description
`url`	No	Try every task on this URL instead of the test's own, for this walkthrough only
`personas`	No	Who tries the tasks (default: a first-time visitor, a careful less-confident user and a busy expert). Describe how each person uses the web, not only demographics.
`surveyId`	Yes
`personaIds`	No	Saved synthetic personas instead of personas
`questionId`	Yes	The usability_test question (from survey_get)
`clientRequestId`	Yes	A new random UUID for each new walkthrough
`successCriteria`	No	What counts as done, by task id (from survey_get); one check per line

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 7, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Beyond the annotations (which only declare non-read-only, open-world, idempotent, non-destructive), the description discloses three high-value traits: the call is asynchronous and returns immediately, idempotency is keyed on clientRequestId, and the run consumes QuestionPunk AI credits. The cost disclosure and async/polling contract are exactly what an agent needs before invoking.

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?

Four compact sentences, each carrying distinct information: what runs, how to override the URL, that it is async with a named poll target, and the idempotency/cost contract. The core action is front-loaded with zero filler.

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 7-parameter, nested-object, async tool with an output schema, the description covers the critical non-obvious pieces (async polling, idempotency, credit consumption, URL scoping). Minor gaps remain, such as behavior when personaIds and personas are both supplied or what happens on insufficient credits, but nothing essential to invoking it correctly is missing.

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 already 86%, so the baseline is 3, but the description adds real meaning: url applies to this walkthrough only and the stored test keeps its own URL, and clientRequestId is the idempotency key that makes repeat calls return the same walkthrough. It does not further illuminate personas vs personaIds or successCriteria, leaving those to the schema.

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 opens with a specific verb and resource ("Run an AI walkthrough of an existing usability test") and immediately explains the mechanism: each persona attempts each task in a real headless browser with grading. This distinguishes it clearly from siblings like usability_test_create_from_url (creates a test) and usability_test_findings_get (retrieves results).

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?

It gives concrete routing guidance: poll usability_test_findings_get after starting, and pass url to retry the same tasks against a new deploy. It does not explicitly state when *not* to use it (e.g., to create a new test from a URL, use usability_test_create_from_url), but the operational context is clear enough for correct selection.

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

All QuestionPunk 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.

Resources

Need Help?