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

With annotations covering safety hints, the description still adds real behavioral context: a concrete price ($0.015/call), a determinism guarantee, primary-source citation, and a billing policy that errors and unverified rules are never charged. The schema's x_payment field covers the payment handshake. It loses a point for not clarifying that this is a side-effect-free calculator while readOnlyHint=false, which could make an agent wonder whether calling it mutates anything.

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?

Pricing and the two modes are front-loaded ahead of the parameter requirements, and the whole thing is compact. The final clause restates the `mode` enum description word-for-word, which is dead weight in an otherwise efficient definition.

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?

Given a present output schema (no need to explain returns), full schema coverage, and annotations covering hints, the description supplies the remaining essentials: cost, billing policy, mode selection, and the statutory basis. The only residual gap is the internal structure of the `hours` object, which is minor for a paid, deterministic calculator.

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 baseline is 3, and the description's mode sentence is a near-verbatim duplicate of the `mode` property description rather than added meaning. Crucially it does not explain the shape of the nested `hours` object or how regular vs. overtime hours are distinguished, which is the one place the schema ('Hours worked') is genuinely ambiguous.

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?

Names a specific computation (overtime premium pay under Labor Standards Act Art.37, plus Article-36 limit check) with the legal basis, which is an unusually concrete verb+resource statement. It even enumerates the two internal capabilities. It stops short of 5 because it never distinguishes itself from payroll-adjacent siblings such as jp_payroll_net or jp_payslip_audit, leaving the agent to infer which tool owns overtime math.

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 mode breakdown ('pay' vs 'check36') tells the agent which parameters each path needs, which is functional routing. However, that is parameter guidance rather than use-case guidance: there is no statement of when to pick this tool over a sibling, no prerequisites, and no exclusions. Usage is implied, not stated.

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