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

Annotations already declare a non-read-only, non-destructive, closed-world write. The description adds genuinely new behavior: cards land in the first list by default when `list` is omitted, and the agent must ask the user when several classes exist. It omits what the response contains, but the mutation semantics themselves are well disclosed.

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?

Front-loaded with the core action, then telegraphic parameter notes, then the class-selection rule. Dense and efficient, though the parameter shorthand makes it read like a cheat sheet rather than prose.

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 4-parameter create tool with no output schema, the description covers the operationally critical points: default list, personal board, and the multi-class ambiguity rule. Missing return-value expectations (e.g. created task IDs) keep it from a 5.

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 50%, so the description must compensate. It does add meaning for `list` (defaults to first list) and clarifies `mine`/`personal`, but it merely restates what the schema already says for `mine` and `personal`, and leaves class_id, title, description, and the tasks-array item structure unexplained.

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?

Specific verb (legt an) plus resource (eine oder mehrere Karten im Aufgaben-Board einer Klasse) with explicit scope. It is clearly distinguishable from update_task/delete_task/save_task_list siblings, which mutate or manage rather than create cards.

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?

Gives explicit routing logic: personal=true for the teacher's own board, otherwise class/class_id, and 'ohne class/class_id/personal: die einzige Klasse; bei mehreren nachfragen' resolves the ambiguity case. It does not name sibling alternatives (update_task, save_task_list) that an agent might confuse with this, so it falls short of a 5.

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