Bank Statement to CSV (Tanod)

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

Goes far beyond the annotations (which only give readOnly/openWorld/idempotent/destructive hints), disclosing cost (USD 0.02, no free tier), latency (1-10 s, 0.2 s/page), limits (200 pages, 413 over 5 MB with no charge), retention behavior ('not logged; result kept only with output url (24 h)'), input parsing coverage (12 languages, 3 layouts), and a security note to treat page text as untrusted data rather than instructions. No contradiction with the annotations.

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 purpose and routing, then grouped into output shape, formats, parsing coverage, error codes, limits, and pricing. Information-dense with heavy semicolon packing, but every clause carries operational value; only the return-shape enumeration is arguably redundant against the output schema.

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?

Despite an output schema existing (so return values need not be described), the definition is complete for a paid, quota-limited conversion tool: cost, timing, page/size caps, failure modes (422 no_text_layer, 413), retention, and docs link are all present. Nothing an agent needs before calling is missing.

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%, so the baseline is 3, but the description adds semantics the schema does not: the OFX/QIF year-in-date requirement that conditions the `format` choice, and the retention consequence of `output: url` that keeps the file out of the context window.

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+resource ('turn a PDF bank statement into dated transactions') and immediately scopes itself against the sibling table extractor with 'For any other table use extract_pdf_tables.' An agent can distinguish this from extract_pdf_tables, extract_pdf, and convert_document_to_markdown without opening a 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?

Explicit trigger ('when an agent must turn a PDF bank statement into dated transactions for bookkeeping or import') plus an explicit exclusion routing other tables to extract_pdf_tables. It also states prerequisites (run OCR first for scanned input; OFX/QIF need a year in every date).

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