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

Annotations declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false, and the description adds real behavioral context beyond them: the default confirm=false creates only a "Vorschlag" (proposal) the teacher manually accepts in the calendar, not a committed entry. It doesn't describe return payload or permission requirements, but the suggestion-vs-committed distinction is the crucial behavioral trait for this mutation.

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?

Three efficient sentences in German: verb+resource first, then the confirm=false default with its rationale and source-tracking guidance, then the confirm=true exception. Every sentence adds meaning; only slight compression of the source_ref/source_note parentheticals could tighten it further.

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 non-destructive mutation tool with annotations covering the safety profile and no output schema, the definition supplies the pivotal decision (confirm semantics) and mail-provenance guidance. It stops short of explaining the alternative editing sibling or the effect of prepare/show_parents, but the schema documents those conditional flags, leaving the agent able to call it correctly.

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 33% schema coverage, the description carries weight and does so for the most important parameter: confirm gains the semantics of "proposal vs. confirmed entry," which the schema leaves bare. It also explains the purpose of source_ref (Message-ID) and source_note (sender/subject) in the mail-provenance flow, though from_mail is only covered by the schema and several nested fields are not addressed.

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?

"Legt Termine an" is a specific verb+resource that clearly states this tool creates calendar appointments, distinguishing it from the update_/delete_/list_calendar siblings by verb. However, it never explicitly routes the agent away from update_calendar_event for modifications, so sibling differentiation is left implicit.

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 explicit conditional guidance for the key decision: confirm=false is the default and produces a proposal that the teacher must accept, used when events come from emails (with source_ref/source_note), and confirm=true only when the teacher names the event themselves. This is clear when-to-use logic, though it doesn't mention the sibling update_calendar_event for editing existing events.

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