Skip to main content
Glama

scobees_create_gliederung

Create a folder or phase in a scobees learning path, set task order locking, and add HTML descriptions, colors, or a cover image.

Instructions

Legt eine Gliederungsstruktur (Ordner/Phase) in einem Lernpfad oder einer anderen Gliederung an. Beschreibung ist HTML (h2, p, strong, em, u, a, span style=color). solve_order=after_solving sperrt jede Aufgabe der Gliederung, bis die davor abgegeben ist (Standard: frei). Optional mit eigenem Kachelbild (cover_image_path) und Farbe; ohne Bild zeigt scobees das Standardbild.

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": {
      "parent_id": "<parent_id>",
      "name": "<name>"
    },
    "name": "scobees_create_gliederung"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYes
colorNoHex-Farbe der Gliederung#00838F
parent_idYesLernpfad- oder Gliederungs-ID
solve_orderNoBearbeitungsreihenfolge der Aufgaben in dieser Gliederung: none = frei (Standard); after_solving = nach Reihenfolge; after_selfcorrection = nach Selbstkorrektur; after_teacher_correction = nach Korrektur durch die Lehrkraft
cover_image_pathNoLokaler Pfad zu einem Kachelbild (PNG oder JPG; live geprüft mit PNG bis 1,3 MB). Quadratisch anlegen – scobees beschneidet die Kachel quadratisch – und ein Motiv wählen, das klein noch erkennbar ist.
description_htmlNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.13
    • addedInput schema / properties / solve_order
      Added value: +{
      +  "description": "Bearbeitungsreihenfolge der Aufgaben in dieser Gliederung: none = frei (Standard); after_solving = nach Reihenfolge; after_selfcorrection = nach Selbstkorrektur; after_teacher_correction = nach Korrektur durch die Lehrkraft",
      +  "enum": [
      +    "none",
      +    "after_solving",
      +    "after_selfcorrection",
      +    "after_teacher_correction"
      +  ],
      +  "type": "string"
      +}
  2. Changed2 schema fields changedv0.1.10
    • addedInput schema / properties / color
      Added value: +{
      +  "default": "#00838F",
      +  "description": "Hex-Farbe der Gliederung",
      +  "type": "string"
      +}
    • addedInput schema / properties / cover_image_path
      Added value: +{
      +  "description": "Lokaler Pfad zu einem Kachelbild (PNG oder JPG; live geprüft mit PNG bis 1,3 MB). Quadratisch anlegen – scobees beschneidet die Kachel quadratisch – und ein Motiv wählen, das klein noch erkennbar ist.",
      +  "type": "string"
      +}
  3. First observedv0.1.0

TDQS

A4/5.0
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 non-obvious behavior: after_solving locks every task in the Gliederung until the preceding one is submitted, the default is free ordering, and omitting an image yields a standard tile. It does not mention permissions, whether the name must be unique, or what the call returns, which matters for a create operation with no annotations.

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 opening sentence front-loads purpose, followed by HTML allowances, solve_order semantics, and image/color options in a compact block with no filler. A few clauses duplicate schema descriptions (hex color, square cropping) and could be trimmed.

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 a six-parameter create tool with no annotations and no output schema, the description covers the unusual semantics well but omits the return value (presumably the new Gliederung ID, needed to nest tasks under it) and any permission or precondition notes. That leaves a real gap an agent would otherwise have to discover by trial.

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 67%, and the description compensates for the undocumented description_html parameter by listing the supported HTML tags (h2, p, strong, em, u, a, span style=color). It also restates the after_solving/default semantics of solve_order and the standard-image fallback for cover_image_path, adding behavior beyond the schema's descriptions.

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?

The description opens with a specific verb-plus-resource: it creates a Gliederungsstruktur, glossed as 'Ordner/Phase', inside a Lernpfad or another Gliederung. That gloss plus the nesting scope makes it distinguishable from siblings such as scobees_update_gliederung or scobees_create_aufgabe without opening any schema.

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 rather than stated: the agent can infer this is the creation step for a folder/phase inside a parent path, and the solve_order note implies the sequencing use case. There is no explicit when-to-use or when-not guidance, and no routing to update_gliederung or move for restructuring existing nodes.

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