Skip to main content
Glama
Sign In
skepsis

skepsis

by ionpetro
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

Answer a question

answer

Grade a learner's reply in a Greek-root lesson session, returning feedback and the next question or session summary with XP, streak, and missed questions.

Instructions

Grade the learner's reply to the current question in a session and get feedback plus the next question (or the session summary with XP and streak). Pass the learner's reply as given: an option number, the option text, 1/2 for Greek or not, pieces in order for build questions ("2 1" or "tele phone"), or pairs like "1b 2a 3d" for matching. Missed questions come back at the end.

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": {
      "session_id": "<session_id>",
      "response": "<response>"
    },
    "name": "answer"
  }
}

Input Schema

NameRequiredDescriptionDefault
responseYesThe learner's reply.
session_idYesSession id from start_lesson or review.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.3/5.0
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 disclose meaningful behavior: it grades, returns feedback plus the next question or a session summary with XP/streak, and resurfaces missed questions at the end. It omits what happens on invalid or duplicate replies and whether the call advances session state irreversibly.

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?

Three sentences, front-loaded with the core action and return value, followed by the format rules and one behavioral note. The parenthetical examples are dense but each earns its place by disambiguating input encoding.

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, yet the description adequately covers the return payload, the input encodings, and end-of-session behavior. The remaining gap is error and edge-case handling (expired session, malformed response), which an agent would still have to discover by trial.

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

Parameters5/5

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

Schema coverage is 100%, so the baseline would be 3, but the description goes well beyond it by explaining the semantics of `response` per question type — option number, option text, 1/2 for Greek or not, ordered pieces like "2 1" or "tele phone", and pairs like "1b 2a 3d". An agent could not infer these encodings from the schema alone.

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?

States a specific verb and resource: 'Grade the learner's reply to the current question in a session' and names the return payload (feedback, next question, or session summary with XP and streak). It does not explicitly contrast itself with siblings like start_lesson or review, so the differentiation is inferable ('current question in a session') rather than stated.

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?

Gives clear context for invocation (answering the current question in an existing session) and detailed how-to guidance for the reply format per question type. It stops short of explicit exclusions such as what to do if the session has ended or the answer was already submitted, so no alternative routing is spelled out.

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

Deploy Server

Other Tools