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

With readOnlyHint/openWorldHint/destructiveHint already declared, the description adds real value: it discloses that header VAT is derived by summing net bases per rate, that nothing is persisted, and that no API key is required. These are behaviors an agent cannot learn from the annotations. It does not discuss failure modes, but the essentials are covered.

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 tight sentences: purpose and inputs first, derived behavior second, non-side-effects and auth last. No filler, and the most decision-relevant facts are front-loaded.

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 17-parameter nested builder that already ships an output schema, the description covers purpose, derivation rule and side-effect profile adequately. Gaps remain around validation failures (e.g. exemptionBasis required when a line uses vatRate 'zw') and the meaning of optional fields, but the tool is callable correctly from this plus the schema.

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 coverage is only 35% across 17 parameters, so the description carries a large compensating burden. It clarifies the seller/buyer/lines grouping and the VAT-aggregation rule, but says nothing about the date fields, currency, iban, splitPayment or the zv/exemptionBasis coupling, several of which have no schema description at all.

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?

States a specific verb and resource (build a sales invoice XML in FA(3) schema, variant 3) plus the inputs it consumes. It implicitly separates itself from generate_correction_xml by naming a *sales* invoice and from any send path by stating it does not send to KSeF. It stops short of naming a sibling explicitly.

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 negative framing (does not send to KSeF, does not store, callable without an API key) usefully signals this is an offline builder step rather than a submission, which helps an agent place it in a workflow. However, there is no positive 'use this when' statement and no pointer to generate_correction_xml for corrections or validate_ksef_xml to check the result, so the routing is left to inference.

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