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

Beyond annotations (idempotent, non-destructive), the description discloses partial-update semantics ("Nur die Felder senden, die sich ändern sollen; alles andere bleibt"), cascade effects of duration changes (via schema for minuten: "Alles Folgende rückt nach"), fixed-time locking semantics for beginnt_um, and that empty strings delete zusatz/nachbereitung. This adds substantial behavioral context not present in the annotations.

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 two short paragraphs, front-loaded with the core purpose, then ownership and deletion boundaries. Every sentence provides distinct information: what changes, how to identify, partial-update semantics, when to copy instead, and what cannot be done. No filler.

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 13-parameter mutation tool with no output schema, the description covers identification, partial updates, ownership constraints, deletion boundary, and key behavioral side effects (time locking, shifting chain). It falls just short of full completeness because a few parameters (ziel, titel, inhalt, material, trainerhinweis) have no description in either schema or main text, forcing the agent to guess from names. Error/return behavior is also not addressed, but annotations mitigate some gaps.

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?

The description clarifies how to identify the target module (Tag + nummer from session_lesen) and the partial-update principle, which adds meaning beyond the schema. However, schema coverage is only 62%, and the description does not compensate for undocumented parameters like ziel, titel, inhalt, material, or trainerhinweis – it merely lists their names. The schema descriptions for some params (art, beginnt_um, minuten, zusatz, nachbereitung) already carry the load; the description adds modest value.

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 opens with a specific verb and resource: "Ändert ein einzelnes Modul einer eigenen Session" and enumerates the exact fields (Titel, Dauer, feste Uhrzeit, etc.). It also explicitly disclaims deletion ("Löschen kann dieses Werkzeug nicht"), which distinguishes it from other mutation tools like module_hinzufuegen or modul_verschieben.

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 gives a clear when-not: "Gehört die Session jemand anderem, nimm zuerst session_kopieren", naming the alternative tool and the condition that triggers it. It also states a boundary (no deletion, user does it in the app), and specifies how to address the module (via Tag and nummer from session_lesen).

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