Skip to main content
Glama
Sign In

Kora

by io.github.onboardly-workspace
OverviewDiscussionsAdmin

Practice KNM exam questions

practice
Read-onlyIdempotent

KNM (Kennis van de Nederlandse Maatschappij) practice questions in Dutch, like the real exam. action 'next' returns a question with lettered choices (optionally by theme), without the answer. action 'answer' with question_id and the user's letter returns whether it is right, with an explanation. Each answer also returns a short progress value that holds this conversation's answer count; passed back as progress, the count continues. Free sample of Kora's KNM bank.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "action": "<action>"
    },
    "name": "practice"
  }
}

Input Schema

NameRequiredDescriptionDefault
themeNoOptional theme for 'next', e.g. healthcare, work, housing, government.
actionYes'next' for a new question, 'answer' to check the user's choice.
choiceNoFor 'answer': the user's letter, A, B or C.
progressNoThe progress value from the latest practice result in this conversation, if there is one. It holds only answer counts.
question_idNoFor 'answer' (or to fetch a specific question with 'next'): the question id.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / progress
      Added value: +{
+  "description": "The progress value from the latest practice result in this conversation, if there is one. It holds only answer counts.",
+  "maxLength": 200,
+  "type": "string"
+}
  2. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare read-only, non-destructive, idempotent, closed-world behavior, so the bar is lower. The description still adds real context beyond them: 'next' deliberately omits the answer, 'answer' returns correctness plus an explanation, and the progress value is per-conversation and only continues the count when passed back. Return-shape behavior is disclosed even though no output schema exists.

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?

The core behavior is front-loaded and ordered by action ('next' then 'answer' then progress), which matches how an agent would call it. It is dense but nearly every clause carries information; the trailing 'Free sample of Kora's KNM bank' is promotional framing that does not help invocation.

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?

With no output schema, the description carries the burden of describing returns and does so for both actions (lethered choices without the answer; correctness plus explanation). It stops short of describing error cases (invalid question_id, stale progress) or the size/scope of the sample bank, which for a stateful two-action tool would be the remaining useful detail.

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 baseline would be 3; the description earns extra by explaining the stateful semantics of 'progress' (this conversation's answer count, continued when passed back) and by clarifying that question_id can be used with either action. Theme, choice and action semantics are largely mirrored from the schema rather than extended.

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 (KNM exam practice questions in Dutch, exam-style) and the two concrete operations ('next' returns a question with lettered choices; 'answer' checks a letter and returns correctness plus explanation). It is specific enough that an agent knows exactly what it does, but it never contrasts itself with the sibling tools (knm_facts, which_exam, inburgering_help), so sibling differentiation is left implicit.

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 gives clear mode-selection guidance: 'next' for a new question, 'answer' to check the user's choice, and notes that 'next' can be narrowed with a theme or a specific question_id. What is missing is any statement of when to prefer this tool over the sibling fact/exam tools, so there is no explicit exclusion or alternative routing.

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

All Kora toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources