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

Annotations say readOnlyHint=false and openWorldHint=true, so the agent already knows this writes something and hits external registries. The description adds real context beyond that: it names the persisted artifact and its contents (MF request IDs, timestamps, findings, SHA-256), the date-sensitivity of the whitelist lookup, and the >15 000 PLN regulatory flag. It does not say where the PDF lands or what happens when a check fails.

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?

Two sentences, front-loaded with the precondition and then the concrete actions, then the artifact contents and the threshold rule. Dense but every clause carries information; only the exact placement/format of the PDF is left implicit.

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 6-parameter composite with no output schema and a write annotation, the description covers the workflow, the external systems consulted, and the shape of the produced artifact (request IDs, timestamps, findings, hash). Missing only file destination and failure behavior, which are minor for correct invocation.

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 33% (date and invoice only), so the description has to carry the rest. It does clarify the semantic roles of nip (contractor tax ID), account (bank account matched against the whitelist), and date (payment date driving the lookup), and ties amount to the 15 000 PLN rule. However currency and invoice are never explained, so the gap isn't fully closed.

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?

Specific verb set and resource: verify NIP + bank account on the MF white list for a given date, check KRS and VIES, and emit a 'proof of due diligence' PDF. The PDF artifact plus the art. 117ba OP / MPP threshold rule is what separates it from the overlapping siblings (check_vat_whitelist, vies_check, get_krs_extract, contractor_due_diligence), which each do one leg of this composite.

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?

Opens with an explicit trigger condition: 'Before paying a Polish contractor', which tells the agent exactly when this tool applies rather than the single-registry siblings. No when-not guidance or named alternatives, so it falls short of the routing precision seen in the top calibration example.

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