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

Adds substantial behavioral context beyond the annotations: default assignment to the owner, notification behavior depending on an external setting whose default is off, and the guarantee that the response reports what was actually sent. It also clarifies side-effect boundaries (no invoice, no customer communication), with no contradiction with readOnlyHint=false, openWorldHint=true, or destructiveHint=false.

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?

Four purposeful sentences arranged in order of importance: core action first, mandatory-person rule second, notification side-effect third, and negative scope last. No filler or repetition; the caps on 'JEDER', 'KEINE', and 'AUS' are effective emphasis.

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 create tool with no output schema, the description covers the essential behavioral rules, defaults, and side-effect exclusions, and even previews the response's key content. It leaves the exact response shape unspecified and does not restate the two-step idempotency protocol in the description, though that protocol is well documented in the schema, so a small gap remains.

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 description coverage is 100%, so the schema already documents all 8 parameters. The description mostly summarizes fields already visible in the schema and repeats the mitarbeiter default; the notification caveat adds context but is not parameter-level semantics, so the baseline 3 is appropriate.

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 specific action ('Legt einen neuen Auftrag an') and resource, lists core fields, and adds explicit negative boundaries ('Legt KEINE Rechnung an und schreibt dem Kunden nichts') that separate it from invoice- and communication-related siblings like rechnung_anlegen or rechnung_versenden.

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?

Clearly indicates when to use it (creating a new order) and gives decision-relevant constraints: a responsible person is mandatory, owner is assigned by default, and notifications depend on the Betrieb's Aussenwirkung setting. It does not name alternative tools explicitly (e.g., auftrag_aendern or angebot_anlegen), so the routing is clear but not fully explicit.

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