Skip to main content
Glama
mcp-feature-test

mcp-feature-test

by linuxrrze

Probe non-spec form fields (elicitation)

elicit_format_probe
Read-only

Probes how clients handle non-spec form-elicitation schema features—color, time, regex, nested objects, free arrays, and file-like fields—by showing one dialog per variant and reporting each result.

Instructions

Show form-elicitation dialogs that use schema features OUTSIDE the MCP spec (format "color", format "time", a regex pattern, a nested object, a free-text array, a file-like data-url field), one dialog per probe, and report what the client did with each. variant picks one probe; "all" runs them one after another.

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_format_probe"
  }
}

Input Schema

NameRequiredDescriptionDefault
variantNoall = every probe in sequence; or one of: pattern, color, time, nested_object, free_array, fileall

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A3.9/5.0
Behavior4/5

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

Beyond readOnlyHint=true, the description discloses operationally important behavior: one dialog per probe, sequential execution under 'all', and that results report what the client did with each field. This prepares an agent for multiple blocking interactive dialogs, which the annotations alone do not convey.

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?

A single dense sentence with no filler — the action and scope come first, the probe inventory follows parenthetically, and the variant behavior closes it out. Nothing repeats what the schema already encodes verbatim.

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 one-parameter diagnostic tool with no output schema and readOnlyHint coverage, the definition is nearly complete. The only remaining gap is the shape of the per-probe report, which is described only as 'what the client did with each' rather than what fields it returns.

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% and the enum is self-documenting, but the description still adds meaning: 'file' is clarified as 'a file-like data-url field' and 'free_array' as 'free-text array', and 'all' is defined as running probes in sequence. That goes modestly beyond the raw enum values.

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 states a specific action (show form-elicitation dialogs) and a precise scope (schema features OUTSIDE the MCP spec), then enumerates the probes. This distinguishes it from generic siblings like elicit_all_field_types by making 'non-spec features' the defining trait, though it never names an alternative explicitly.

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?

It explains how to drive the tool ('variant picks one probe; "all" runs them one after another') but gives no when-to-use versus when-not guidance — nothing says why an agent would pick the color/time probes over elicit_all_field_types or pick_color. Usage is implied by the probe list rather than stated.

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