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

Annotations only declare readOnlyHint and openWorldHint; the description adds substantial behavioral context beyond them: a 5-credit cost per call, an explicit guarantee that the XML is self-validated and never returned invalid, named error modes (engine_busy, engine_timeout), and the important caveat that amounts are written as given and not computed or corrected. That last point is exactly the kind of non-obvious behavior 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?

Front-loaded with the one-line purpose, then Input, then Returns, then Credits — a predictable and scannable layout. Every sentence carries operative information (size limit, defaults, conditional requirement, no auto-correction, cost); there is no filler or repetition of the title.

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 single-parameter, nested-object generation tool with an output schema present, the description covers everything needed: input shape and limits, defaults, conditional field requirements, output fields, validation guarantee, error modes and cost. Nothing material is left for the agent to infer before invoking it.

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 already 100% and the single parameter is documented, so the baseline is 3; the description goes further by enumerating the main invoice fields, stating defaults ("ubl", "en16931"), the date format (YYYY-MM-DD), and the conditional dependency between flavor and buyer_reference. It adds real semantics the schema's flat field list does not carry, though it does not detail nested structures like seller, buyer, lines or tax_breakdown.

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 first sentence names a specific verb (create), the artifact (EN 16931 e-invoice), the output format (UBL or CII XML), and the input form (from JSON). It is clearly distinguishable from siblings like convert_invoice, parse_invoice, validate_invoice and render_invoice, which are named in the sibling list and not conflated here.

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?

Gives strong contextual guidance: 4 MB input cap, default values for syntax/flavor, and the conditional rule that flavor="xrechnung" requires buyer_reference (Leitweg-ID BT-10). It also names the failure conditions (invalid input, failed self-check, engine_busy, engine_timeout). It stops short of explicitly routing the agent away from siblings such as validate_invoice or convert_invoice, so it is clear but not a full when/when-not statement.

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