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

With no annotations present, the description carries the full behavioral burden. It usefully discloses that totals and VAT breakdown are computed and that the return is {valid, xml, totals, errors}, which is real information even without an output schema. However, it says nothing about side effects, persistence, auth requirements, rate limits, or what 'valid' truly gates.

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 purpose is front-loaded before the dense field spec, and every line carries information with no filler. It is delivered as one long unbroken paragraph with sparse structure, which hurts scannability given the volume of nested fields.

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 tool with no annotations, no output schema, and 0% schema coverage on a nested object, the description supplies the input contract in detail and even sketches the return shape. Missing pieces are auth/permission requirements, whether anything is persisted, and richer error semantics beyond the generic 'errors' key.

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 0% and the single parameter is a deep object, so the description must compensate — and it largely does, enumerating format enum values, date formats, currency, line items with vat_category codes, and payment fields, with optionality marked by '?'. The buyer/seller '...' ellipsis and unclear required-vs-optional within nested objects leave some residual ambiguity, capping this below 5.

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 gives a specific verb+resource+standard: 'Create a validated EU e-invoice (UBL 2.1) from simple JSON'. This clearly separates it from validation/sending siblings by signalling generation of the document. It stops short of explicitly naming an alternative like validate_einvoice or send_einvoice_sandbox, so sibling differentiation is left implicit.

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?

Nothing states when to use this tool versus validate_einvoice, send_einvoice_sandbox, or einvoice_route, nor any prerequisites or ordering in the workflow. The use case is inferable from 'create' and the 'returns {valid, xml...}' note, but no explicit context or exclusions are given.

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