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

Adds substantial context beyond the annotations: it spends credits (billed per request or per page, project pricing, EUR 25 free credit), the result contains personal data and is returned only to the caller (server never stores or logs it), plus operational limits (30s URL download, 50-page timeout). None of this is derivable from readOnlyHint/openWorldHint/destructiveHint.

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-loads the credit warning and the extraction scope before the handling warnings and input rules. Long but dense, with each sentence carrying billing, privacy, or input-selection 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?

No output schema exists, but the description effectively names the returned fields and warns that they contain personal data, so an agent knows what comes back. Minor gaps remain around error behavior and whether large documents must be split, though page_ranges and the 50-page timeout partially cover that.

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 a real constraint not expressed in the schema: exactly one of url/data_base64/file_id must be supplied (the schema marks all 8 params optional with no oneOf). The cost implication of configuration_slug is also noted.

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 and resource ('extract a bank statement') and enumerates the exact fields returned (bank, account holder, period, opening/closing balance, every transaction). This clearly separates it from sibling capture tools such as einvoice, salary slip, or identity.

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?

Gives a strong input-selection rule: 'Give the document as exactly one of url (public https), data_base64 (small files) or file_id (a stored file)', and points to dochorizon_list_configurations for the optional configuration_slug. It does not, however, say when to prefer this over dochorizon_capture_generic or the async capture variants.

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