E-Rechnung erzeugen

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

Annotations already flag a non-idempotent, non-read-only write, but the description goes well beyond them: it warns this writes into real BuchhaltungsButler data, that there is no API endpoint to undo it, that there is no API path to read the resulting invoice back (only the web UI), and that the endpoint applies the strictest field validation in the API. This is exactly the operational caveat an agent needs before calling.

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?

Five dense sentences packed into one paragraph, front-loaded with the purpose and the sibling routing before the validation and irreversibility caveats. Slightly long, but each sentence carries distinct information (routing, required-field deltas, no-read path, irreversibility) rather than filler.

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 28-parameter, 11-required mutation tool this covers the gaps that matter: it duplicates none of the output schema but supplies the irreversibility, the missing read-back path, and the sibling selection rule. Nothing an agent needs in order to call it correctly is missing.

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 baseline is 3, but the description adds real meaning: it calls out which fields become mandatory here (e_invoice_id plus street, zip, city, country, email) and that positions use item_tax_type/item_tax_amount in place of item_vat, an API renaming the schema does not explain. That goes beyond restating the required list.

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 verb and resource ('Erzeugt ... eine E-Rechnung: endgültig, nummeriert, mit PDF und strukturiertem Datensatz nach EN 16931') and immediately names the two closest siblings (bb_invoices_create for the ordinary invoice, bb_invoices_create_draft for a draft). An agent can distinguish this from every other invoice tool without opening a 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?

Explicit when-to-use ('Zu nehmen für Empfänger, die eine E-Rechnung verlangen, etwa öffentliche Auftraggeber') and explicit alternatives with the condition that selects each ('bb_invoices_create erzeugt die gewöhnliche Rechnung, bb_invoices_create_draft einen Entwurf'). 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.