Skip to main content
Glama

HiveLearn

by io.github.williamechevarria
OverviewDiscussionsAdmin

hivelearn_create_quiz_question

Add a question to a quiz. Supply the answer field for the type: multiple_choice → options [{text, is_correct}] with exactly one is_correct:true; multi_select → options with one or more correct; true_false → correct_answer (boolean); fill_in_blank → accepted_answers; matching → pairs [{left, right}]; ordering → items [{text}] in correct order (or with position 1..n).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
itemsNoordering only; correct order is position 1..n, or array order if positions are omitted
pairsNomatching only; at least 2 pairs
pointsNoDefaults to 1
optionsNomultiple_choice (exactly one is_correct:true) or multi_select (one or more). 2-12 entries.
quiz_idYes
sort_orderNo
explanationNo
question_textYes
question_typeYes
correct_answerNotrue_false only
accepted_answersNofill_in_blank only; matched case-insensitively

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changed
    • addedInput schema / properties / accepted_answers
      Added value: +{
+  "description": "fill_in_blank only; matched case-insensitively",
+  "items": {
+    "minLength": 1,
+    "type": "string"
+  },
+  "type": "array"
+}
    • changedInput schema / properties / correct_answer / description
      Previous value: -"For true_false only"New value: +"true_false only"
    • addedInput schema / properties / items
      Added value: +{
+  "description": "ordering only; correct order is position 1..n, or array order if positions are omitted",
+  "items": {
+    "properties": {
+      "id": {
+        "type": "string"
+      },
+      "position": {
+        "maximum": 9007199254740991,
+        "minimum": 1,
+        "type": "integer"
+      },
+      "text": {
+        "minLength": 1,
+        "type": "string"
+      }
+    },
+    "required": [
+      "text"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}
    • changedInput schema / properties / options / description
      Previous value: -"For multiple_choice only; shape: [{text, is_correct}]"New value: +"multiple_choice (exactly one is_correct:true) or multi_select (one or more). 2-12 entries."
    • removedInput schema / properties / options / items / additionalProperties
      Removed value: -{}
    • addedInput schema / properties / options / items / properties
      Added value: +{
+  "id": {
+    "type": "string"
+  },
+  "is_correct": {
+    "type": "boolean"
+  },
+  "text": {
+    "minLength": 1,
+    "type": "string"
+  }
+}
    • removedInput schema / properties / options / items / propertyNames
      Removed value: -{
-  "type": "string"
-}
    • addedInput schema / properties / options / items / required
      Added value: +[
+  "text"
+]
    • addedInput schema / properties / pairs
      Added value: +{
+  "description": "matching only; at least 2 pairs",
+  "items": {
+    "properties": {
+      "id": {
+        "type": "string"
+      },
+      "left": {
+        "minLength": 1,
+        "type": "string"
+      },
+      "right": {
+        "minLength": 1,
+        "type": "string"
+      }
+    },
+    "required": [
+      "left",
+      "right"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}
    • changedInput schema / properties / question_type / enum
      Previous value: -[
-  "multiple_choice",
-  "true_false"
-]New value: +[
+  "multiple_choice",
+  "true_false",
+  "fill_in_blank",
+  "multi_select",
+  "matching",
+  "ordering"
+]
  2. First observed

TDQS

A3.9/5.0
Behavior3/5

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

With no annotations, the description carries the burden of behavioral disclosure, and it clearly identifies the operation as adding a question. It also surfaces correctness constraints, such as exactly one is_correct for multiple_choice, but it does not disclose behavior on validation failure, whether the question is appended immediately, or what is returned.

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 description is a single dense sentence with no filler and it front-loads the purpose. The type-to-answer mapping is compact and scannable, though a short list or explicit bullet structure would slightly improve readability.

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 complex conditional create operation with no annotation support, the description covers the critical cross-parameter rules, namely which answer field to supply for each type, and leaves simpler optional parameters to the schema. It could add a note about response or error behavior, but the invocation-relevant information is largely complete.

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 description maps each question_type to the required answer parameter and its shape, which is the most important semantic linkage beyond the schema. It does not restate every parameter, but it compensates for the moderate schema coverage on the conditional fields where misuse is most likely.

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?

The description opens with a specific verb and resource: 'Add a question to a quiz.' It is clearly distinct from sibling create tools such as create_quiz or create_question_bank_item, and the target resource is unambiguous.

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 gives strong conditional guidance for constructing the answer field per question_type, but it does not explicitly state when to choose this tool over alternatives like update_quiz_question, create_quiz, or create_question_bank_item. The intended use is implied by 'Add a question to a quiz' rather than explicitly contrasted.

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

All HiveLearn 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