Skip to main content
Glama
mcp-feature-test

mcp-feature-test

by linuxrrze

Multi-step wizard (elicitation)

elicit_wizard
Read-only

Walk through a three-step imaginary pizza order, collecting size-dependent toppings and confirming a summary to demonstrate chained elicitation with signed request state.

Instructions

Order an imaginary pizza through a 3-step dialog wizard. Step 2 depends on step 1 (number of toppings depends on size), step 3 shows a summary for confirmation. Demonstrates chained elicitations with signed requestState.

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": "elicit_wizard"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=true; the description adds real behavioral substance beyond that — a fixed three-step sequence, a genuine dependency where the topping count follows the size chosen in step 1, and a confirmation summary at step 3. The signed requestState detail also hints that state is carried between calls. It loses a point for not describing what happens if the user declines, cancels mid-wizard, or what the final response contains (there is no output schema to cover 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?

Three short sentences, front-loaded with the scenario and then the step mechanics; every clause carries information about the flow. The 'imaginary pizza' framing is whimsical but does useful work signalling a demo rather than a real ordering operation.

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 zero-parameter, read-only demo tool with no output schema, the description covers the essential shape: step count, inter-step dependency, and confirmation stage. The main remaining gap is the outcome — what the caller receives on success, failure, or user rejection — which is not covered by any structured field.

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?

The tool takes no parameters, so the baseline is 4. The description nonetheless adds meaning by explaining that the effective inputs are gathered across three sequential dialog steps with step 2 conditioned on step 1, which is information the empty schema cannot convey.

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?

States a concrete action — running a 3-step dialog wizard that collects an imaginary pizza order — and explicitly frames it as a demonstration of chained elicitations with signed requestState. That framing distinguishes it from the single-shot siblings like elicit_confirm and elicit_all_field_types without naming them. It stops short of a 5 because it never says outright which sibling to prefer for non-chained elicitation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: 'Demonstrates chained elicitations' signals this is a demo/probe tool for multi-step flows, so an agent can infer it is the right pick when testing dependent steps. There is no explicit when-to-use, when-not-to-use, or named alternative, and no mention of whether the caller must be prepared to relay user prompts.

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