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

Adds real behavioral context: content preserved, removed from lists and sending, idempotent on re-invocation. But the destructiveHint=true annotation is not reconciled – the description emphasizes that nothing is lost, which an agent might read as non-destructive. No mention of permissions or required state.

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?

Duplicated DE/EN is slightly redundant but front-loads the core action and effect; each clause carries meaning about state and behavior.

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?

No output schema, and while lifecycle behavior is covered, parameter meanings (especially reasoning) and the 'reason' field's purpose or the permission requirements are absent, leaving gaps against a mutation tool with 0% schema coverage.

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 0%, so the description should compensate, yet neither templateId nor the optional reasoning parameter is mentioned. The 'unschädlich/erneut aufrufen' sentence implies idempotency tied to templateId but gives no format or semantic detail.

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+resource ('Archiviert eine Vorlage' / 'Archives a template') and clearly distinguishes it from siblings like template_draft_discard by describing the effect (disappears from lists/sending but kept).

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?

States the effect and that repeated calls are harmless, but never says when to archive versus discard or delete (e.g. template_draft_discard). Usage is only implied.

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