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

Annotations already declare read-only, idempotent, non-destructive behavior. The description goes beyond these by explaining partial payment display (Rest neben Betrag, Zeile als teilbezahlt), the sorting behavior for `nur_offen` (by age of overdue), and critical handling of UUIDs (never ask humans to input/repeat them). These are concrete behavioral traits not present in annotations.

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?

The description is informative but slightly verbose. It front-loads the output fields and then explains partial payments, the `nur_offen` use case, the `suche` behavior, and the UUID rule. Each sentence earns its place, but the UUID guidance could be more tersely phrased. Still, it is well-structured and not bloated.

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?

Given the annotations (read-only, non-destructive, idempotent) and complete schema coverage, the description covers all essential aspects: what fields are returned, the behavior of filters (nur_offen, suche), sorting, and the critical UUID handling. It also implies how results feed into `rechnung_ansehen`. No missing information for an agent 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?

Schema description coverage is 100%, so all six parameters have descriptions. The tool description adds extra meaning for `nur_offen` (unpaid, sorted by overdue age) and `suche` (finds paid/cancelled/drafts), enriching the agent's understanding beyond the schema's basic descriptions. It does not address `von`, `bis`, `anzahl`, or `nur_ueberfaellig` in the description, but these are adequately covered by the schema, so the added value is sufficient.

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?

The description clearly states it lists invoices with key fields (number, customer, amount, status, due date, outstanding balance) and differentiates from siblings like `rechnung_ansehen` (view specific) and `rechnung_anlegen` (create). It also names follow-up tool `rechnung_ansehen` for found IDs. The verb 'Listet' is specific and the resource is unambiguous.

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?

It provides contextual usage: 'der übliche Einstieg für offene Posten' and explains the `suche` parameter as a way to find specific invoices including paid, cancelled, and drafts. It also advises using internal identifiers only for follow-up tools. However, it does not explicitly contrast with other search siblings (e.g., `auftraege_suchen`, `kunden_suchen`) or list conditions when this tool is not appropriate, leaving some inference to the agent.

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