Skip to main content
Glama

Conversion QA Walk

qa_walk

Conversion QA Walk™: every step a new customer takes, from the page they land on to the screen after paying (entry, signup, verify, first-screen, first-win, upgrade, checkout, after-payment, billing), walked in the founder's Chrome at desktop and phone width, in-app browsers read from the code. With no input: the site read from outside (entry pages, the signup page, the pricing page, the misses the server already sees), the steps, 38 checks by area (copy, errors, layout, forms, in-app browsers, email, the first result, conversion, payment, speed) with how to make each, a measure script and a paint-time script, the rules (ask the founder before signing up with their email and a password you set, disable that account after, never pay), the last walk, and a test account still to disable. Call again with record for what the walk found: every step (walked, or why not), the issues (check, step, device, severity blocker, major or minor, what was seen, the fix, evidence), the checks that passed, and account { email } when a test account was made; returns the report, blockers first, and what a re-walk no longer sees. disabled: true once the test account is disabled. skip: issue ids the founder will not fix. Free.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "qa_walk"
  }
}

Input Schema

NameRequiredDescriptionDefault
skipNoIssue ids (qa:...) the founder will not fix: never shown again
recordNo
disabledNotrue once the walk's test account is disabled

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, openWorldHint=true and destructiveHint=false, and the description adds substantial context beyond them: the operational rules (ask the founder before signing up with their email and a password you set, disable that account after, never pay), the fact it is free, and that 'disabled: true' marks the test account as torn down. It also discloses the return shape (report with blockers first, and what a re-walk no longer sees). The one gap is that it never says what happens if record is submitted twice or how skip interacts with re-walks beyond 'never shown again'.

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 purpose is front-loaded, which is good, but the body is a dense run-on of comma-separated lists with a trademark symbol and long enumerations of step names and check areas. Much of it earns its place, yet the single-block formatting makes it harder to scan than it needs to be for a tool with three top-level parameters.

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?

This is a complex tool with nested objects and no output schema, and the description covers both invocation modes, the rules of engagement, and the shape of the returned report. An agent could call it correctly from this text alone. It falls short of 5 only because the re-walk and idempotency behavior around record and disabled is left implicit.

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 67% and the description compensates well: it explains skip as issue ids the founder will not fix, record as the walk's findings broken into every step (walked, or why not), issues with check/step/device/severity/what/fix/evidence, the checks that passed, and account { email } when a test account was made. The nested shape of record is therefore legible before opening the schema. Only the 'url' field on record is left unexplained.

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 opens with a specific verb and resource: walking every step a new customer takes, from entry through billing, in the founder's Chrome at desktop and phone width, plus in-app browsers read from code. That is far more concrete than the name alone. It does not, however, contrast itself with any sibling tool, so an agent must infer why it would pick this over 'verify' or 'app_audit'.

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?

Usage is clearly split by mode: call with no input to get the outside-read site, the 38 checks by area, the measure and paint-time scripts, the rules and the last walk; call again with record to submit what the walk found. That is explicit when-to-use guidance for both invocations. What is missing is any exclusion or named alternative for when this walk is the wrong tool.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources