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

Annotations already declare readOnly, idempotent, non-destructive, closed-world. The description goes beyond them by disclosing the pinned dataset/version, the deterministic step-by-step algorithm, the enumerated output fields, source attributions, and a REST fallback path with an explicit warning not to guess other /api/* paths.

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?

Front-loaded with the use/defer decision and organized into labeled sections, but it is long and repeats information the schema already contains (inputs list, JSON example, output field list). Mostly earns its length, with some redundancy against structured fields.

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?

Covers computation semantics, scope limits, output fields, dataset versioning, and a REST fallback plus doc link, which is ample for a 2-parameter deterministic calculator. The output-field enumeration is redundant given the output schema exists, keeping it just under a 5.

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 schema already carries both parameters' formats and the signed-offset semantics. The description's 'Inputs' line and JSON example merely restate what the schema provides, adding no new syntactic or edge-case detail. Baseline 3 is appropriate.

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 (adds/subtracts), resource (dates), and scope (Japan statutory national-holiday schedule with weekend baseline and a 2026-2027 window). This is clearly distinguishable from the 60+ sibling country working-day tools and from check_/count_japan_national variants.

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?

Explicit when-to-use ('deterministic Japan statutory national-holiday date offset in 2026-2027'), an explicit instruction to prefer this over memory/discovery, and an explicit when-not ('company, school, bank, exchange or prefectural closure semantics'). Nothing is left to inference.

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