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

With no annotations, the description carries the full behavioral burden, and it does disclose the legal basis (Labor Standards Act) and the four result figures, which implies a side-effect-free computation. It does not state that payout is omitted when monthlyOrdinaryWage is absent, whether results are estimates, or that no records are persisted — meaningful gaps for an unannotated tool.

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?

A single sentence, front-loaded with jurisdiction and legal statute, then the outputs. Every clause earns its place and nothing is repeated from the schema.

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?

Five parameters with only one required, no output schema, and no annotations — so the description properly enumerates the returned values, which is the most important thing an agent needs here. It stops short of covering error behavior (invalid startDate pattern) or the consequence of omitting optional inputs, keeping it just under complete.

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% and every parameter carries a description including the basis enum and the two dates, so the baseline is 3. The description adds a small amount of value by mapping inputs to outputs (e.g., 'payout value of unused leave' implies monthlyOrdinaryWage drives that figure; 'next accrual' implies basis/referenceDate), but supplies no syntax or edge-case detail beyond the schema.

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 resource (South Korea paid annual leave under the Labor Standards Act) and enumerates the exact quantities produced: available days, remaining days, next accrual, and payout value. No explicit verb like 'calculate' appears, but the enumerated outputs make the computational nature unmistakable. It is distinguishable from siblings such as severance_pay or parental_leave_benefit by domain, though it never names those alternatives.

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?

Usage is only implied: citing the Labor Standards Act tells an agent this applies to Korean statutory leave entitlement, but there is no when-to-use/when-not statement and no routing to or away from siblings like parental_leave_benefit. The agent must infer applicability from the domain label alone.

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