Daily Tutor MCP

Overview Schema Source Related Servers Discussions Admin

check_answer

Grades a user's raw quiz answer, automatically scoring exact verdicts and recording XP/streak, or returns guidance for manual judging and reformatting when needed.

Instructions

EVALUATE step 1: ALWAYS call this first with the user's raw reply. For letters, ordering, matching, true/false verdicts and accepted commands it grades exactly and records XP/streak itself (auto_graded=true): then just explain. Otherwise (auto_graded=false) it tells you how to judge, and you finish with record_result. bad_format=true means ask the user to reformat; the question stays open.

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": {
      "question_id": "<question_id>",
      "user_answer": "<user_answer>"
    },
    "name": "check_answer"
  }
}

Input Schema

Name	Required	Default
`user_id`	No	default
`question_id`	Yes
`user_answer`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.0Nov 2, 2026

TDQS

A4.2/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does it well: it discloses the auto_graded fork, that XP/streak are persisted as a side effect, that the question stays open on bad_format, and that the agent must finish the grading via record_result. It never explains what the remaining payload looks like, so it falls just short of complete.

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?

Front-loaded with the 'ALWAYS call this first' rule, and every sentence carries behavioral information. The dense run-on phrasing around auto_graded takes a second read but wastes no space.

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?

No output schema and no annotations, but the description covers the control flow, side effects, and the failure mode. The gaps are parameter sourcing (question_id/user_id) and return payload, which keep it from a 5.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate, yet it only implies that user_answer is the raw reply. question_id (where it comes from, e.g. get_pending_question) and the user_id default are entirely undocumented in both schema and description.

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?

States a specific verb and resource: it grades the user's raw reply and, for certain answer types, records XP/streak itself. It is explicitly positioned as 'EVALUATE step 1' and contrasted with record_result, so an agent can tell it apart from every sibling without opening the schema.

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

Usage Guidelines5/5

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

Gives an explicit ordering rule ('ALWAYS call this first with the user's raw reply'), enumerates the answer types it handles automatically, and names the follow-up path (call record_result when auto_graded=false). The bad_format=true branch also says what to do next.

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