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

With minimal annotations (only readOnlyHint=false, destructiveHint=false), the description carries the behavioral burden and delivers richly: bilden creates TWO tracks immediately, feld switching deletes nothing (texts persist in background), aufloesen lengthens the day by reverting to sequential counting, and the gruppe ID source is specified via session_lesen's 'parallel' field. The repeated 'nothing is deleted' claims are consistent with destructiveHint=false, so no contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core concept and the key scheduling rationale before the bulleted action list. The structure with bolded action names and behavioral consequences is scannable. It is somewhat verbose - the 'Warum es dieses Werkzeug braucht' paragraph runs long - but each sentence contributes either conceptual clarity or a side-effect warning, so it mostly earns its place.

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

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

For a complex tool (8 params, 5 actions, mutation semantics, no output schema), the description covers the full action set, side effects, the source of the gruppe ID, and the required user warning. The only real gaps are the return value (not disclosed, but acceptable for a mutation tool) and explicit differentiation from sibling tools like modul_aendern, which the scheduling rationale partially addresses.

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

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

Schema coverage is 100% - all 8 parameters have descriptions specifying which action each serves (tag for bilden/benennen, nummer for bilden/benennen, gruppe for schiene/feld/aufloesen). The description adds conceptual domain context (what a Schiene is, how groups relate to modules) that enriches understanding, but it doesn't introduce per-parameter semantics beyond the schema. Baseline 3 is appropriate since the schema already carries the burden.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb (setzen/manage), the resource (parallel groups - multiple modules running simultaneously), and enumerates all five actions (bilden, schiene, benennen, feld, aufloesen) with their effects. It explicitly differentiates itself from the naive alternative of creating multiple modules with the same time, making it distinguishable from sibling tools like module_hinzufuegen without opening schemas.

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

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

The description explains when this tool is needed rather than 'mehrere Module mit derselben Uhrzeit', including the concrete scheduling consequence (5x45min counts as 45min, not 225min). It also tells the agent to warn the user before aufloesen because the day becomes longer. However, it doesn't explicitly name sibling tools as alternatives or state when NOT to use it beyond the implicit scheduling scenario.

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