Skip to main content
Glama

Axad

Start a learning path

start_runbook
Idempotent

Start a learning path for the learner in a language, or return their place in it if they started it before. Returns the current step: what it asks, which tools and widgets it uses, and when it is done.

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": {
      "runbook": "<runbook>",
      "lang": "<lang>"
    },
    "name": "start_runbook"
  }
}

Input Schema

NameRequiredDescriptionDefault
langYes
runbookYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false, so the description is not carrying the safety burden alone. It still adds real context beyond them: it clarifies the resume behavior in user-facing terms and describes exactly what the response contains — the current step, the tools and widgets it uses, and its completion condition.

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?

Two sentences, both front-loaded with the highest-value information — what the call does and what comes back. No filler, no restatement of the title, and the return description is packed into a single clause.

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?

With no output schema, the description correctly spends its words on the return shape, which is the right call. It is still incomplete for a mutating, state-producing tool: the learner identity is left implicit, the accepted formats of both required parameters are unstated, and nothing explains what happens to an in-progress path if start_runbook is called again with different arguments.

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 both required parameters (lang, runbook) are bare strings with no documented format, and the description must compensate. It only obliquely implies that lang is a language and runbook is a learning path; it never says whether the language is a code or a name, or whether the runbook is a slug, id, or title, so an agent cannot reliably construct either argument.

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 ("Start a learning path") and immediately adds the upsert semantics ("or return their place in it if they started it before"), which separates it from a pure creator. It does not name any sibling such as next_step or list_runbooks, so the boundary with the rest of the catalog is still inferred 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 Guidelines3/5

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

Usage is implied by the start-or-resume phrasing, which tells an agent this tool is the entry point into a runbook. However, there is no explicit when-to-use versus when-not guidance, and no pointer to next_step for advancing or to list_runbooks/browse_catalog for discovering a valid runbook value.

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.