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

With no annotations, the description carries the full burden and excels: it discloses non-custodial behavior, per-row txHash and Basescan links, dedup by txHash, optional block-time filters, and the crucial window-honesty caveat about undated receipts being excluded and reported in summary.undatedExcluded.

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 dense but every sentence earns its place. It uses clear signposts like 'ACCOUNTING EXPORT' and 'WINDOW HONESTY' to structure information, and the length is justified by the tool's complexity — covering purpose, columns, dedup, window logic, and caveats without redundant words.

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 4 parameters, no output schema, and a subtle edge case (undated receipts), the description is remarkably complete. It explains the CSV columns, the pointer/chain trust model, dedup behavior, window filtering, the undatedExcluded counter, and gives a recovery instruction (re-run without window). This is fully actionable.

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?

Even though schema coverage is 100%, the description adds meaningful semantics beyond property names: brand slugs the filename, receipts are expected to carry txHash, and the from/toBlockTime parameters are explained in terms of window filtering and the undated-exclusion behavior. This goes well beyond the schema's simple descriptions.

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 clearly states the tool's function: turning verified receipts into an accountant-ready CSV for QuickBooks/Xero/Excel. It names the specific verb 'export' and the resource (receipts to CSV), and its emphasis on accounting/basescan distinctiveness sets it apart from sibling receipt and payment tools.

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?

It provides clear context for when to use: finance/accounting export needs, with a strong rationale ('pointer to the chain'). However, it does not explicitly name when not to use it or an alternative tool such as till_receipt or till_check_payment, so it stops short of the full 5.

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