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

With no annotations at all, the description carries the full burden and does so: it discloses deterministic arithmetic checks (opening + movements = closing, line-by-line running balance, credit/debit totals, IBAN checksum), that wrong signs are silently corrected and flagged, that the file is not stored, the page cap, and the exact price (€0.1 per statement, charged to the Bearer API key). Those are precisely the mutation/cost/retention facts an agent needs before calling a paid endpoint.

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 transformation and the output payload, followed by validation behavior, then limits/cost, then parameters — a sensible order with no filler sentences. It is dense and long, but the length is justified by 0% schema coverage; the arrow-chain phrasing and the parameter recap add only mild redundancy.

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 paid, unannotated extraction tool, everything material is present: input formats, extracted fields, validation semantics, correction/flagging behavior, page limit, pricing model and billing target, data-retention stance, and per-parameter defaults. An output schema exists, so the enumerated return fields are a bonus rather than a gap-filler.

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 0%, so the description must compensate, and it documents all four parameters with meaning and defaults (url source, categorize, csv, language with a concrete default list en,de,fr,es,it,nl,pl,uk). The one weakness is a type conflict: the description frames categorize and csv as booleans ("categorize=true", "csv=true") while the schema declares them as strings, which could lead an agent to send the wrong value type.

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?

"Bank statement PDF, scan or photo → account, IBAN, period, opening and closing balance and every transaction" names a concrete input class and enumerates the exact output fields, so an agent can tell instantly that this is statement-specific extraction rather than generic OCR (ocr) or a different document type (invoice_parse, pdf_text).

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?

Accepted inputs (PDF, scan, photo), the 30-page ceiling, and the per-10-page billing implicitly tell the agent when this tool fits, and the `language` parameter signals the scan/OCR case. It stops short of an explicit exclusion or sibling routing (e.g. "use ocr for non-financial documents, pdf_text for raw text"), so the alternative selection is left to inference.

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