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

Annotations already declare readOnlyHint/openWorldHint/destructiveHint=false, so the safety profile is covered. The description adds real context beyond that: it downloads into the 'Faktury z KSeF' list, the returned field set, the date semantics, the exclusion of already-booked documents, and the Cotlet API key requirement. Note a mild tension: 'downloads invoices into a list' reads like an import side effect while readOnlyHint=true, though this is ambiguous enough not to be a clear contradiction.

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?

Front-loaded with the core purpose, then field contents, date semantics, exclusion rule, and auth. It is slightly redundant, stating the 'not yet booked' condition in both the opening and via 'Documents already booked are not returned', but every element is substantive.

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, the description carries the return-value burden and does so by enumerating the item fields (seller document number, KSeF number, document type, seller NIP, issue date, net/gross). Auth requirements and filtering scope are covered; pagination/limits are unaddressed but no pagination parameter exists.

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 documents the single issued_from parameter as the first seller issue date. The description reinforces this and adds the disambiguating nuance that the date is the seller issue date, not the date sent to KSeF, which is genuinely useful for interpreting the filter.

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 states a specific resource and scope: KSeF purchase invoices that suppliers sent and the user has not booked yet. Combined with the verb 'list/return', an agent can distinguish this from siblings like ifirma_book_ksef_purchase_invoice and ifirma_list_invoices without opening any schema.

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?

It gives clear context for when this applies ('you have not booked yet', 'Documents already booked are not returned'), which strongly implies the unbooked-invoice retrieval workflow that precedes booking. It does not explicitly name the booking sibling as the follow-up action, so it stops short of full when/when-not/alternative guidance.

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