Invoice Bridge

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

No annotations exist, so the description carries the full disclosure burden. It does creditably report the rate limit (3 documents/day UTC/IP), a size ceiling, and the important 'No document storage' data-handling guarantee, but it says nothing about what a validation run produces — whether violations are returned as a list with line references, whether a failed document raises an error, or whether results are idempotent. For a validator with zero annotation coverage, that silence is a major gap.

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 definition is compact and free of filler, but it is front-loaded with validator/KoSIT version numbers and a licence URL rather than the statement of function an agent needs first. The licence link is arguably the least decision-relevant element yet occupies the closing position.

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?

With no output schema and no annotations, the description must cover both input contract and return behavior. It handles the quota and storage posture but leaves the response shape — the single most important thing for an agent deciding whether to call a validator — completely undefined.

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 single parameter 'xml' has no schema description (0% coverage), so the description must compensate. It partially does by stating '60,000 UTF-8 bytes/document', which explains the maxLength: 60000 constraint in terms of bytes — useful, though it does not clarify that maxLength is measured in characters, nor that the input is the raw XML document text rather than a URL or path.

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 name and the mention of 'XRechnung 3.0.2 / KoSIT configuration 2026-08-31' imply that the tool validates XRechnung e-invoices, but the description never actually states a verb such as 'validates' or 'checks' — the purpose is inferred rather than declared. There are no siblings to distinguish from, so the lack of differentiation does not hurt, but the opening is spent on version metadata instead of a plain statement of function.

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?

There is no guidance on when to use this tool, what inputs are acceptable (e.g. UBL vs CII syntax, minimum required fields), or what to do when validation fails. The only usage-shaped content is the free-tier quota and the byte cap, which constrains volume but not applicability.

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