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

Annotations already establish readOnlyHint=true and openWorldHint=false, and the description adds real context on top: it reads the PDF, applies cent-level reconciliation, returns a yes/no verdict plus the specific rows that break, and notes the cost model ('Free with a PivotBank account'). It stops short of covering malformed PDFs or statements lacking a running-balance column.

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?

Three tight sentences: trigger first, mechanism second, output and pricing last. No redundancy, no restatement of the tool name, and the most decision-relevant information (when to invoke) is front-loaded.

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 read-only validation tool with no output schema, the description covers what is checked, what is returned, and the pricing/auth caveat. The one gap is edge-case behavior when a statement has no running-balance column to reconcile against, which an agent might need to set expectations.

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 the nested statement object (file_id, file_name, mime_type, download_url) and the pdf_base64 fallback are already fully documented in the schema. The description only says 'Reads the PDF' without adding format constraints, size limits, or guidance on choosing the attachment path over base64, 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?

States a specific verb and resource: it reads a bank statement PDF and reconciles every row against the statement's own running balances, with the exact arithmetic rule spelled out (opening + in - out = closing, to the cent). This is clearly distinct from siblings convert_statement and summarise_spending, which transform or aggregate rather than validate.

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 an explicit triggering condition: use when the user asks whether a statement is complete, correct, genuine, or why its numbers don't add up. It does not name the alternatives (e.g. convert_statement for format changes, summarise_spending for totals) or state when this tool is the wrong choice, but the positive routing is unambiguous.

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