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

Goes well beyond the annotations by disclosing overwrite semantics ('students ersetzt die komplette Liste', 'Ersetzt den ganzen Plan') and the default-preserving nuance for colors ('ohne colors bleiben die bisherigen'). That replacement/default distinction is exactly the context an agent needs and is not derivable from readOnlyHint=false / destructiveHint=false; note the mild tension with destructiveHint=false, though the description itself supplies the missing warning.

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?

Dense but front-loaded: mode selection first, then the destructive replacement facts, then the nested structure with concrete examples. No filler sentences; the nested timetable explanation is compressed to the point of being slightly cryptic but remains parseable.

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 mutation tool with 8 properties, nested objects, no output schema and only 50% schema coverage, the description supplies the mode discriminator, the overwrite semantics and the nested timetable encoding. Remaining gaps (return value, partial-update behavior for omitted fields, zero required parameters) are minor relative to what is covered.

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?

With only 50% schema coverage, the description carries real weight: class_id drives mode selection, students means first names only and replaces the list, and the nested timetable shape (periods as {start,end}, days keyed by weekday 1–5 with lesson index, "" meaning free period, optional colors) is fully decoded. name, grade, subject and the timetable_csv alternative are left to the schema, so it is not exhaustive.

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?

States a precise verb pair and resource (create/update a class) and immediately gives the discriminator: with vs. without class_id. An agent knows exactly what operation it will trigger without inspecting the schema.

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 create-vs-update condition is spelled out explicitly in the first clause, plus the critical constraint that students and timetable are full replacements rather than merges. It stops short of naming exclusions or a sibling alternative, but no sibling in the list competes for this operation.

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