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

Given no annotations were provided, the description carries the full behavioral burden and excels. It discloses failure modes (rejected calls name the BT-xx rule violated), side-effect-free execution ("Nothing is stored"), and numerous non-behaviors: no Peppol, no PDF, no multi-rate support, no Schematron validation. This is exemplary transparency.

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 long but every section earns its place: core behavior, critical tax-rule guidance, a 'what this does NOT do' list, and data-retention disclosure. It is front-loaded with the one-sentence purpose and then organized into scannable blocks, though the tax-rule detail could arguably be trimmed for the most common cases.

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 complex nested invoice schema and no output schema, the description covers the essential behavioral gaps: return format (XML as text), error/rejection behavior (returns named BT-xx failures), constraints (one tax rate, one category, bare XML), and non-goals (no ZUGFeRD, no Peppol, no persistence). This is unusually complete for a high-complexity tool.

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 names fields like taxCategoryCode and buyerReference, but the description adds critical semantics not inferable from types alone: tax category S implies a specific reduction, AE requires BT-120, the Leitweg-ID must go into buyerReference (BT-10), and the single-rate limitation. It also gives email/contact guidance missing from the schema.

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 opens with a clear verb+resource: "Builds a ... electronic invoice ... and returns the XML as text." It precisely distinguishes itself from siblings by naming what it does NOT do (no ZUGFeRD, no Peppol, no PDF) and what it uniquely handles (EN 16931 rule pre-checks), so an agent can select it without opening the 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 routing guidance is everywhere: use validate_einvoice for a second opinion, use check_leitweg_id for BT-10 lookup, and avoid this tool for multi-rate invoices or when a Schematron-level guarantee is required. Conditions like 'tax category S requires reduction', 'AE requires BT-120', and 'public sector => put Leitweg ID in BT-10' give concrete call-time decision rules.

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