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

Annotations only cover readOnly and openWorld, so the description carries real behavioral weight: it discloses the paid model ($0.001 USDC on Base via x402), the failure mode (unpaid call returns PaymentRequired), and the exact remedy (retry with _meta["x402/payment"]). That is exactly the non-obvious operational context an agent needs before invoking.

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?

Purpose is front-loaded, followed by payment mechanics and an example arg. Every sentence earns its place, though the trailing example args string partially duplicates the schema's example field.

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 single-parameter tool with no output schema, the description supplies the missing pieces: it hints at the return content (validation result, normalised number, bank code) and fully explains the payment flow. Adequate and slightly above minimum for this complexity level.

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 goes further by decoding the expected format as BB-bbbb-AAAAAAA-SSS and supplying a concrete example arg, which clarifies what a valid input looks like beyond the schema's bare 'e.g.' sample.

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 (validate) and resource (NZ bank account number check digit), and enumerates the actual operations: check-digit validation via IRD algorithms A-G/X, normalisation to BB-bbbb-AAAAAAA-SSS, and bank-code identification. This clearly separates it from siblings like nz_validate_ird and nz_validate_nzbn, which validate different identifier types.

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?

The narrowly scoped purpose makes usage strongly implied (feed it a bank account number to validate it), but there is no explicit when-to-use statement, no prerequisites, and no direct routing against sibling validators such as nz_validate_ird. Guidance is inferred rather than stated.

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