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

Beyond the readOnlyHint=false annotation, the description discloses highly relevant behavioral traits: the invoice is validated, standard invoice attributes come from the connected Betrieb, repeated calls with the same bestellnummer do not create duplicates, and the call consumes monthly quota. This is exactly the kind of side-effect and idempotency context an agent needs before invoking a write tool.

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?

Three dense sentences carry the full behavioral contract without repeating schema information. The primary action is front-loaded, and each sentence adds a distinct, valuable fact: what is created, what is auto-derived, and the idempotency/quota constraints.

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 mutating tool with nested schema objects but no output schema, the description covers the essential operational context: validation, formats, auto-derived fields, idempotency, and quota. It does not describe the return value or how to access the created invoice afterward, which is a minor gap but not critical for correct invocation.

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?

Even though schema field descriptions already cover bestellnummer and recipient details, the description adds semantic context not in the schema: sender, invoice number, and payment terms are supplied by the Betrieb rather than the caller, and bestellnummer acts as the idempotency key. With 67% schema coverage and rich nested parameter descriptions, the small additional parameter-level context 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 states a specific action and resource ('Erzeugt eine geprüfte E-Rechnung') with explicit formats (XRechnung, PDF, ZUGFeRD), making the tool's purpose unmistakable. It is clearly distinguished from sibling read/search/validate tools (rechnung_lesen, rechnung_pruefen, rechnungen_suchen) by the create verb and invoice-generation context.

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?

The description implies when to use the tool—whenever a validated E-Rechnung must be created—and conveys key operating conditions such as derived sender data, idempotency, and tariff quota. However, it does not explicitly state when not to use it or name an alternative sibling (e.g., use rechnung_datei to retrieve the file, or pflicht_pruefen to validate beforehand), so usage guidance remains implied rather than explicit.

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