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

With no annotations, the description carries the full burden and does well: it discloses tolerance of malformed input, the shape of the answer (each violation with rule identifier and business term, plus the set of rules checked), an explicit limitation ('never claims full compliance'), and a cost of 1 credit. Only idempotency/non-mutating nature and any size or timeout limits are left unstated.

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 sentences, front-loaded with the purpose and then the behavioural contract. Nearly every clause earns its place, though 'the arithmetic that most often gets invoices rejected' is mild editorial colour rather than operational information.

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?

There is no output schema, so the description correctly compensates by describing the return payload (violations, rule ids, business terms, rules actually checked) and the scope limitation. For a one-parameter tool with deep nested invoice objects that is close to complete, missing only error/edge-case behaviour such as what happens with a structurally invalid payload.

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 100% and there is a single parameter, so the baseline is 3. The description adds meaning beyond the schema by stating that the invoice payload may be deliberately incomplete or malformed and that this is acceptable input rather than an error, so it goes slightly above baseline.

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 (checks) and resource (invoice data) against a named standard (EN 16931 business rules) and enumerates the checked categories: mandatory fields, code lists, VAT category consistency and arithmetic. This clearly separates it from extract_invoice and generate_invoice, which do entirely different things with the same resource.

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 line 'Accepts incomplete or malformed data on purpose, since that is what you want checked' tells the agent the condition under which this tool is the right one, i.e. pre-validation of possibly-broken input. It does not explicitly name a sibling as an alternative or state when not to use it, so it falls short of a 5.

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