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

With no annotations, the description carries the full burden. It discloses important behavioral traits: 'Stateless — es wird nichts gespeichert' (stateless, nothing is stored), which is valuable. It also mentions support for multiple positions, VAT categories, discounts/surcharges, and payment details. However, it does not mention plan restrictions (e.g., logo only in Pro/Ultra) or explicit error behaviors, but those are covered in the schema. Overall, the description provides meaningful behavioral context beyond what the schema offers.

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 two sentences, immediately front-loading the core purpose and then providing key capability details. Every sentence carries useful information: the first defines the tool's function and formats, the second summarizes supported features and statelessness. There is no fluff or redundant restating of the tool name.

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 tool's complexity (20 parameters, nested objects, no output schema), the description is fairly complete. It states what it creates, the format options, supported features, and that it is stateless. It does not explicitly describe the return value or response structure, but since there is no output schema, this is a minor gap. The description covers the essential behavioral context for an agent to invoke 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 description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds some high-level context (e.g., 'mit Leitweg-ID für B2G' hints at buyer_reference, 'alle USt-Kategorien' maps to vat_category), but it does not delve into individual parameter semantics beyond what the schema provides. This aligns with the baseline of 3 for high schema coverage.

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 with a specific verb and resource: 'Erstellt aus strukturierten Daten eine valide E-Rechnung' (creates a valid e-invoice from structured data). It distinguishes itself from siblings (validation, consistency check, XML extraction) by focusing on creation, and even specifies the two output formats (ZUGFeRD-PDF and XRechnung-XML).

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 provides clear context on when to use the tool: when you have structured data and need to create an e-invoice. It implies the tool is for generation rather than validation or extraction, which aligns with sibling tools, but it does not explicitly name alternatives or exclusions. The context is sufficiently clear for an agent to select this tool for invoice creation tasks.

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