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

The description discloses critical behavioral aspects: it is deterministic, cites primary sources, errors and unverified rules are never billed, and the cost is $0.02/call. It also explains the payment mechanism via x_payment header and the option to omit it to receive payment requirements without being charged. This is rich transparency beyond any annotations (none provided), covering reliability, billing, and authentication in an unusually thorough manner.

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 two sentences: the first packs the core functionality and per-item verdicts, the second adds billing and reliability guarantees. Every word earns its place; it is front-loaded with the primary purpose and ends with important caveats without fluff.

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 complex tool (auditing, statutory tables, multiple inputs, billing), the description covers essential aspects: what it computes, verdict types, determinism, citation, billing, and payment alternatives. No output schema exists, but the description's clarity about verdicts (match/explainable/mismatch) partially substitutes. The only missing piece is explicit guidance on required vs optional parameters, but the schema already marks prefecture and payslip as required, reducing need.

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?

The description provides substantial parameter context: it mentions 'statutory premiums and withholding tax' and 'official tables', which relate to prefecture, age, as_of, and standard_monthly_yen. It also explains the x_payment parameter's purpose in detail (payment header, optional, billing behavior). However, it does not explain payslip structure or the exact semantics of each parameter (e.g., age vs. as_of), but with 17% schema coverage, the description compensates better than baseline, scoring slightly above 3.

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 starts with a specific verb ('Audit') and resource ('Japanese payslip'), then details the auditing process: recomputing statutory premiums and withholding tax from official tables, diffing against actual amounts, and providing per-item verdicts. It clearly distinguishes itself from sibling tools like jp_payroll_net and jp_social_insurance by focusing on auditing existing payslips rather than calculating net pay or social insurance amounts.

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 description clearly defines the tool's scope (auditing Japanese payslips) and the context in which it should be used. It implicitly differentiates from sibling tools by focusing on 'recompute and diff' rather than calculation or estimation. However, it does not explicitly state when NOT to use it or mention alternatives, so it loses a point for not providing explicit exclusions.

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