Skip to main content
Glama
Sign In

UX Pilot

by ai.uxpilot
OverviewDiscussionsAdmin

design

UX Pilot's AI designs, with credits. action: agent (makes or changes screens or a new React app from a brief, on a tier: standard, pro or ultra; poll get_job), react (screens into a React app), react_edit (change a React app from a prompt), flowchart, flowchart_edit. Ask the user first: the first call answers with a confirmationToken.

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": "design"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionNoWhat to run.
paramsNoThe action's fields. guide({ topic: "<tool>.<action>" }) lists them.
confirmedNotrue only after the user agreed to this call.
confirmationTokenNoThe token the first call answered with.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare non-read-only, open-world, non-idempotent, non-destructive behavior, and the description adds meaningful extra context: operations consume credits, calls are gated by a user confirmation token, and long-running work must be polled via get_job. It does not explain what an edit does to existing screens or whether changes are recoverable, so it is not fully transparent.

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?

Two dense sentences, front-loaded with the identity of the tool and then the action menu, with the critical confirmation rule placed last so it is not lost. Nothing is padded, though the comma-spliced action list is terse to the point of being slightly hard to scan.

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 multi-action dispatcher with an opaque nested params object, the description covers what to call, the confirmation flow, and the polling continuation, and it points to guide for per-action fields. With no output schema, it never says what a returned job or design artifact looks like, which is the main remaining gap.

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 100%, so the baseline is 3, but the description adds real meaning: each action enum value is glossed, the 'agent' action's tier values (standard, pro, ultra) are revealed even though the tier lives inside the opaque params object, and the confirmed/confirmationToken handshake is explained. The nested params fields remain undocumented except by delegation to guide.

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 names the resource (AI-generated designs, screens, React apps, flowcharts) and enumerates the five concrete operations with short parenthetical glosses for each. An agent can tell roughly what each action does and that results are asynchronous jobs. It does not explicitly contrast itself with siblings like generate_media or edit, so it stops short of a 5.

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 states a mandatory workflow condition ('Ask the user first: the first call answers with a confirmationToken') and routes follow-up work to get_job for polling, which is real when-and-how guidance. It does not say when NOT to use this tool or which sibling covers adjacent cases such as plain image generation.

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

All UX Pilot toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources