Convert bank statement to CSV/Excel

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

Annotations declare readOnlyHint=false with destructiveHint=false, and the description is consistent with that: it writes a CSV rather than altering the source, and 'Runs locally' corroborates openWorldHint=false, which is useful context the annotations don't state in words. It adds genuinely behavioral detail beyond the annotations - running-balance verification and that discrepancies are reported in the result. It stops short of describing error behavior or what the report looks like.

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 action and output target, then the column contract, then the correctness check and locality note - a sensible order with no filler. It is a dense, long single sentence, slightly harder to scan than it could be, but every clause carries 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?

With no output schema, the description correctly takes on the burden of describing the return: per-transaction columns plus a discrepancy report from balance checking. Password and failure-debug paths live in the schema, so the main remaining gap is what the results object looks like structurally and where the CSV path is returned.

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 description coverage is 100%, so password, debug, file_path and output_path are already fully documented at the field level, including the default naming for output_path. The description adds no phrasing-level meaning (no format constraints on file paths, no detail on what 'reports any that don't agree' returns), so baseline 3 applies.

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?

Specific verb and resource: 'Convert a PDF (or CSV) bank statement into a clean CSV.' It also enumerates the output shape (one row per transaction with date, narration, reference, debit, credit, balance, plus category, payee, decoded UPI), which makes the tool unmistakably a converter rather than the sibling analyze_bank_statement. It never names that sibling, so differentiation is implied rather than explicit.

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?

Usage is implied by the input formats it accepts (PDF or CSV) and the conditional guidance in the schema ('If parsing fails...', 'Ask the user; never guess it' for passwords). There is no explicit statement of when to choose this over analyze_bank_statement or what to do with the balance-mismatch report afterwards, so the agent must infer routing.

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