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

Goes well beyond the annotations: discloses a real side effect (temporary PDF created on api.almmity.com, retrievable via unguessable link for one hour, then deleted), that no API key is required, and that the NBP rate lookup is a read-only call against a public API. This is exactly the extra context annotations cannot convey and it is consistent with readOnlyHint=false / openWorldHint=true.

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?

Four tight sentences with the purpose front-loaded and the rate variants immediately after; no filler. It is dense to the point of slight crowding — the PDF lifetime and API-key notes are packed into the same breath as the domain rules — but every sentence carries 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?

For a 10-parameter, nested, open-world tool this covers the things that matter: rate basis, side effects, data retention, authentication, and read-only external access. Return values are largely covered by the output schema, though the many undocumented input fields (iban, place, creditor/debtor) leave some gap in how to fill the invoice and party data.

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 description coverage is only 30% across 10 parameters, so the description must compensate. It does add real meaning for `kind` (mapping handlowe/leczniczy/ustawowe to the +10pp/+8pp/+5.5pp rate rules) and for `compensation` (40/70/100 EUR converted at the NBP euro rate), but it says nothing about iban, place, creditor/debtor, documentNumber, or payWithinDays, leaving more than half the inputs unexplained in both places.

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 (calculate) plus a precisely scoped resource (Polish late-payment interest) with the exact rate formulas spelled out for each of the three statutory regimes. No sibling tool covers this, and the definition names the reference implementation (ksef.almmity.com) so the agent knows the output is authoritative-compatible.

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?

Establishes clear context: it computes interest only, 'does not file anything', and is callable without an API key. That implicitly distinguishes it from siblings like draft_payment_demand or payment_audit_report, but no sibling is named explicitly and no when-not-to-use condition is given beyond the filing exclusion.

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