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

The readOnlyHint annotation already indicates a read-only operation, and the description reinforces this with 'Zeigt' and 'Vorschau'. It also discloses that grouped sums match later invoices to the cent, which is useful behavioral information.

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 compact and focused, using three short sentences to convey purpose, use cases, and an important accuracy guarantee. There is no redundant or irrelevant information.

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 simple read-only query with optional filters, the description provides enough context about output shape (individual items or per-customer sums) and accuracy. It does not mention defaults for omitted von/bis parameters or ordering, but this is minor given the tool's straightforward nature.

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?

The schema already provides 100% parameter coverage with concise descriptions. The description restates the grouping semantics ('einzeln oder als Summe je Kunde') but does not add substantial extra detail beyond the schema, such as defaults or validation rules for the optional date range.

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 the tool's purpose: showing recorded but not yet invoiced services, either individually or aggregated per client. The title and description make it easy to distinguish from sibling tools like offene_posten or leistungen_abrechnen.

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 explicitly gives use cases: checking what has not yet been invoiced in the current month and as a preview before monthly closing. It does not name sibling alternatives explicitly, but the intended scenarios are clear enough.

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