Rechnung erzeugen

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

With annotations present the bar is lower, and the description still adds substantial context beyond them: the write lands in real BuchhaltungsButler data, there is no API path to read the invoice or its PDF (only the web UI), there is no currency parameter because API invoices are EUR-only, and there is no endpoint to undo the write. The irreversibility warning sits in mild tension with destructiveHint=false, though creating a record is additive rather than a destructive update, so it is complementary rather than contradictory. Auth needs and rate limits are not covered.

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 correctly: what it creates, then when to use it and which sibling to prefer, then the operational caveats. Dense and mostly waste-free, though the worked example and the sibling detour lengthen the opening considerably and could be trimmed.

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 27-parameter irreversible write with an output schema, the description covers the decisive operational facts: finality trigger, alternatives, no read-back path, EUR-only, no undo. It stops short of documenting failure modes (e.g. duplicate invoicenumber handling) or delivery of the PDF, but the core is sufficient to call the tool 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 coverage is 100%, so the schema already carries the field-level detail (including the item_amount vs item_single_price distinction and the parallel-array conversion). The description still contributes beyond the schema by flagging the absent currency parameter and illustrating a realistic call ('10 Std. Beratung zu 120.00 je Stunde'), which prevents a foreseeable misuse.

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 states a precise verb and resource ('Erzeugt ... eine endgültige Ausgangsrechnung, eine Gutschrift oder ein Angebot') and immediately qualifies the scope ('endgültig', nummeriert, PDF, Ausgangsbeleg). It explicitly separates itself from the two nearest siblings, so an agent can route without opening any schema.

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 gives an explicit when-to-use trigger ('Zu nehmen, sobald der Vorgang final ist') plus a concrete example, and names both alternatives with the condition that selects them: bb_invoices_create_draft for a draft without numbering, bb_invoices_create_einvoice for an e-invoice with per-position tax type. Nothing is left to inference.

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