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

Despite sparse annotations, the description extensively discloses side effects (credit consumption), asynchronous batch behavior, time-limited download links, and the essential role of the 'summary' field. This goes well beyond the annotation hints and prevents misuse.

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?

The description is long, but every clause addresses a distinct need: input methods, batch mode, output formats, and response handling. It is front-loaded with the core purpose and then flows logically. A few minor redundancies (e.g., multiple places mentioning mutual exclusivity) could be trimmed, but it remains scannable.

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 tool with 7 parameters, asynchronous batch semantics, multiple output formats, and credit costs, the description covers all functional gaps: file references, batch admission, polling, download links, summary field, credits, and page limits. The presence of an output schema means return-value details are already covered, so this is complete.

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?

With zero schema description coverage, the description carries the full burden—and excels. It explains the semantic differences between pdf, pdf_url, pdf_file, upload_id, upload_ids, and output_format, adding critical context like 'never encode it yourself' and the mutual exclusivity of parameters.

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 opens with a clear, specific verb+resource: 'Convert a bank statement PDF into structured data or a spreadsheet.' It distinguishes itself from siblings by detailing when to use get_statement (for batch polling) and request_upload (for hosts without file references), making it obvious this is the conversion tool.

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?

Explicitly explains when to use each of the four file-reference methods (pdf_file, pdf_url, upload_id, base64), calls out mutual exclusivity for batch uploads, and directs users to get_statement for polling when using the asynchronous batch form. It also clarifies default vs. alternative output formats.

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