Skip to main content
Glama
mcp-feature-test

mcp-feature-test

by linuxrrze

Graphical dialog (MCP App)

open_dialog_lab
Read-only

Opens an interactive graphical dialog with a color picker, slider, star rating, drag-to-reorder list, and drawing canvas to collect user input for later reading via dialog_lab_results.

Instructions

Open the "Dialog Lab": an interactive graphical dialog (MCP Apps / ui:// resource) with a colour picker, slider, star rating, drag-to-reorder list and drawing canvas. The user can submit the result to the server, send it as a chat message, or put it into the model context. Use dialog_lab_results afterwards to read what the user submitted.

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": "open_dialog_lab"
  }
}

Input Schema

NameRequiredDescriptionDefault
itemsNoItems the user should rank by drag & drop
questionNoHeadline shown in the dialogConfigure your dream workspace

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=true; the description adds substantial context beyond that — it identifies the tool as a UI/MCP App resource and implies the call returns before the user acts, since results must be fetched with dialog_lab_results. It does not state whether the call blocks, what it returns, or which user action populates the results, so a small gap remains.

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 sentences, front-loaded with the action and resource, then the follow-up routing. Every clause earns its place; no restatement of the title or 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?

No output schema exists, and the description correctly redirects the agent to dialog_lab_results rather than pretending to describe return values. Remaining unknowns (blocking behavior, whether the dialog must be re-opened per interaction, client capability requirements) are minor but real for a UI-launching tool.

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 100%, with both 'items' and 'question' documented (defaults included), so the schema carries the burden. The description adds no parameter-level detail — notably it never mentions the ranking items list or headline question, even though the text advertises a drag-to-reorder list.

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?

States a specific verb ('Open') and resource (the 'Dialog Lab' UI resource) and enumerates the widgets it contains (colour picker, slider, star rating, drag-to-reorder list, drawing canvas). An agent can distinguish it from dialog_lab_submit / dialog_lab_upload / dialog_lab_results because it explicitly describes opening the interface and defers results to a sibling.

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?

Gives clear sequencing guidance: open the dialog, then 'Use dialog_lab_results afterwards to read what the user submitted,' and explains the user-side options (submit to server, send as chat message, put into model context). No explicit when-not-to-use or precondition (e.g., client must support MCP Apps) is stated.

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