Skip to main content
Glama

Создать тест с вопросами

create_test

Тест целиком за один вызов: параметры и вопросы по порядку. Типы вопросов: one (один из списка, ровно один верный), many (несколько верных), text и number (верный ответ в correct_text), open (ответ своими словами; reference_answer и criteria помогают проверке). Куда положить: lesson_id — блоком в конец урока, module_id — итоговым тестом модуля; можно и то и другое, можно ничего.

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": {
      "title": "<title>",
      "questions": "<questions>"
    },
    "name": "create_test"
  }
}

Input Schema

NameRequiredDescriptionDefault
titleYes
lesson_idNo
module_idNo
questionsYes
pass_scoreNo
descriptionNo
max_attemptsNo
Idempotency-KeyNoКлюч повтора, до 120 знаков. Новый на каждое новое создание; тот же, если повторяете этот вызов после ошибки или обрыва: второй раз ничего не создастся, вернётся первый ответ. Ключ помнится сутки.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / Idempotency-Key
      Added value: +{
      +  "description": "Ключ повтора, до 120 знаков. Новый на каждое новое создание; тот же, если повторяете этот вызов после ошибки или обрыва: второй раз ничего не создастся, вернётся первый ответ. Ключ помнится сутки.",
      +  "maxLength": 120,
      +  "type": "string"
      +}
    • addedInput schema / properties / questions / items / properties / correct_text / maxLength
      Added value: +200
  2. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations declare readOnly=false, destructive=false, idempotent=false and openWorld=false, so safety is partly covered; the description adds real behavior beyond that by stating the whole test is created in a single call ('целиком за один вызов') and by spelling out how each question kind's answer is carried. It does not say whether the write is atomic on partial failure, nor does it mention the Idempotency-Key retry behavior (that lives only in the schema), nor any permission requirements.

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 three compact sentences, front-loaded with the atomic-create claim, then question types, then placement. Nothing repeats the name or the schema, though the parenthetical explanation of each kind is slightly dense and could have been table-like.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter mutation tool with no output schema and very low schema coverage, the description covers the hardest parts (question kind semantics and placement) but leaves grading and retry behavior (pass_score, max_attempts, weight, Idempotency-Key) unexplained and never indicates what the call returns. An agent could call it, but would be guessing on scoring parameters.

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 only 13%, so the description must carry the load: it does explain the five `kind` values, that `text`/`number` answers go in `correct_text`, and that `open` uses `reference_answer` and `criteria`, plus the `lesson_id`/`module_id` destination semantics. However, several parameters remain unexplained anywhere in prose — pass_score, max_attempts, weight, description, and the per-option is_correct — so compensation is meaningful but incomplete.

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 opening line 'Тест целиком за один вызов: параметры и вопросы по порядку' states a specific verb (create) and resource (a whole test with an ordered question list), which tells an agent this is an atomic create rather than an incremental add-question flow. It does not explicitly contrast with the read sibling get_test or any build-up alternative, so it stops short of a 5.

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?

Placement guidance is explicit and decision-oriented: lesson_id appends a block to the end of a lesson, module_id makes it the module's final test, and 'можно и то и другое, можно ничего' clarifies that both or neither is valid. It gives no guidance on when to create a test at all versus other content tools, so it is clear context without full exclusion rules.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources