Skip to main content
Glama
Sign In
skepsis

skepsis

by ionpetro
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

Start a lesson

start_lesson

Starts the next Greek-root lesson or a specified lesson and returns teaching cards plus the first question, enabling guided one-question-at-a-time tutoring.

Instructions

Start the next lesson (or a given lesson id like "u1l2", or a unit roundup like "u1-review"). Returns cards to teach and the first question. A lesson is ~3 minutes: guess-first warm-up, new roots/ideas, then practice. Act as a friendly tutor: teach the cards first in your own words, then ask ONE question at a time, wait for the learner's reply, and pass it to answer unchanged. Never reveal the answer before they reply.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "start_lesson"
  }
}

Input Schema

NameRequiredDescriptionDefault
lesson_idNoLesson id from list_course. Leave empty for the next lesson.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.7/5.0
Behavior4/5

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

No annotations exist, so the description carries the full burden, and it does real work: return shape (cards + first question), lesson length (~3 minutes), internal flow (warm-up, new roots/ideas, practice), and a behavioral rule against revealing answers. It does not say whether starting a lesson mutates saved progress or how an invalid lesson_id is handled, which are the remaining gaps for an unannotated tool.

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?

Four sentences, front-loaded with what the tool does and what it returns, then flow, then tutor protocol. No sentence is redundant; the id examples and the answer hand-off rule each carry distinct information.

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

Completeness5/5

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

For a one-parameter tool with complete schema coverage and no output schema, the description supplies purpose, return contents, expected interaction pattern, and safety constraint. Nothing an agent needs to invoke it correctly is missing.

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% and the schema already documents the single optional param, so the baseline is 3. The description adds value beyond it by giving concrete id formats ('u1l2', 'u1-review') and naming list_course as the source of valid ids.

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 (start a lesson), clarifies the two modes (next lesson vs. explicit lesson_id vs. unit roundup) with concrete id examples, and discloses what comes back: teaching cards plus the first question. An agent can distinguish it from list_course and answer from the description alone.

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?

Explicit branching: leave lesson_id empty for the next lesson, or supply an id from list_course. It also names the downstream sibling and the hand-off rule ('pass it to `answer` unchanged') and the constraint 'ask ONE question at a time, wait for the learner's reply'.

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