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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds real substance: a legal cutoff date (as of 2026-11-07), the named source domains behind each rule, the April 2025 給付制限 change, and the explicit 'No yen amounts' limitation. It also carries a clear disclaimer of non-affiliation and non-advice, which is exactly the kind of trust/behavioral context annotations cannot express.

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 purpose, then parameters, then return shape — a sensible order with no filler sentences. It is dense and parenthetical-heavy, but nearly every clause (aliases, thresholds, cite dates) carries information an agent needs, so the length is largely earned.

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?

With 11 parameters and no output schema, the description compensates by listing every returned field group (verdict, immigration, unemployment with waitingDays/restrictionMonths/earliestBenefitDay, health, pension, documents, deadlines, actions, warnings, sources). Combined with the required-parameter flag and the as-of date, an agent has enough to call it and interpret the result without guessing.

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 baseline would be 3, but the description adds genuine meaning: enum aliases for status (技人国, 特定技能, 留学, 家族滞在, 永住) and reason (会社都合 / 自己都合 / 契約満了), plus the eligibility thresholds for insuredMonths (company ≥6 in 1 year, self ≥12 in 2 years). That goes beyond the terse schema descriptions and materially improves how an agent supplies those fields.

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 opens with a specific verb and resource: it 'Applies Japan's post-employment checklist' covering ISA notification, Hello Work eligibility, and health/pension switches. The enumerated output names (immigration, unemployment, health, pension, documents, deadlines) make its scope unmistakable and separate it from siblings such as japan_leaving_tax_check or japan_reentry_deadline_check.

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?

It gives concrete trigger phrases in English and Japanese ('I quit my job in Japan what do I do', '所属機関に関する届出 期限', '任意継続 国保 どっち'), which tells an agent exactly when to route here. It does not explicitly name a sibling it excludes or state a when-not-to-use condition, so it falls short of 5.

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