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

Beyond the annotations (readOnly=false, idempotent=true, destructive=false), it discloses the non-obvious side effect that changing start/end retimes the whole schedule while preserving module durations and parallel blocks, and that the caller need not recompute times. It also documents partial-update semantics (send only changed fields), empty-string clearing, and the ownership constraint. This is substantive context the annotations cannot carry.

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 purpose and the most important guidance are front-loaded, but the text is long and repeats itself: the retiming cascade ("Alle Module ... rücken geschlossen mit", "Du musst also KEINE Uhrzeit selbst ausrechnen") appears twice near-verbatim, and the display-settings paragraph re-lists fields already enumerated in the first line. Each idea earns its place, but the duplication costs space.

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 15-parameter mutation tool with no output schema, the description covers the risky areas well: retiming side effects, partial updates, field clearing, ownership preconditions, and the day-count reduction caveat (detailed in the schema). It could say more about what a successful call returns or how validation failures surface, but nothing essential for correct invocation is missing.

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 93%, so the schema already documents most parameters; the description adds cross-parameter relationships instead of repeating them: beginn_uhrzeit/ende_uhrzeit apply to all days while tageszeiten handles single-day deviations, and the spalten list must be complete rather than partial. It adds real meaning without covering every field (e.g. erster_tag, sprache, art colors are left to the schema).

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 opening sentence names the specific verb and resource ("Ändert die Angaben ZUR Session selbst") and enumerates the editable attributes, so the agent immediately knows the scope. It is explicitly distinguished from modul_aendern/module_hinzufuegen (per-module edits) and from session_anlegen/session_kopieren (creating sessions).

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?

It gives concrete trigger phrases ("nenn die Session anders", "die findet doch in Köln statt", "wir fangen eine halbe Stunde früher an"), explicit exclusions (module duration/text/order and fixed per-module times belong to modul_aendern and module_hinzufuegen), and a prerequisite (if the session belongs to someone else, use session_kopieren first). It also warns against creating a duplicate session and explains why.

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