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

Beyond annotations, the description discloses determinism, a $0.015/call charge, legal-source citation, and a billing guarantee ('errors and unverified rules are never billed') — genuinely useful behavioral context. It does not contradict annotations: idempotentHint=true aligns with 'Deterministic,' and readOnlyHint=false is consistent with the paid computation. Minor gap: it never states what non-read side effect (the charge) entails.

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?

Two tight sentences with no filler: purpose and legal grounding first, then pricing and trust guarantees. Every clause earns its place, and the front-loading lets an agent grasp scope immediately.

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?

The dual-mode design is clear from the description plus the mode enum, but there is no output schema and the description never hints at the return format — a meaningful gap for a paid tool where an agent should know what it gets for $0.015. For a moderately complex 6-param tool with nested objects, this leaves the output contract unspecified.

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 schema already documents all six parameters. The description adds legal framing (Art.37, rounding notice, Article-36) that helps interpret mode and the overtime-related params, but it does not map legal concepts to specific fields. Baseline 3 is correct since the schema carries the burden.

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 names a specific verb-resource pair: 'Overtime premium pay' plus a distinct 'Article-36 limit check,' both anchored to the Labor Standards Act Art.37 and the official rounding notice. This clearly distinguishes it from JP siblings (jp_payroll_net, jp_bonus_net, jp_payslip_audit) and tells an agent it handles overtime-specific Japanese wage computation.

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 two functions (pay and Article-36 limit check) and the legal scoping give an implied usage context, but no explicit when-to-use vs alternatives guidance and no exclusions. An agent must infer that this is the overtime-specific tool among the payroll siblings rather than being told directly.

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