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

Annotations already declare readOnly/idempotent/destructive=false, so safety is covered; the description goes further by labeling itself a 'deterministic, dated table', disclosing the pre-2026-09-30 exception (¥6,000/¥5,500/¥10,000), and disclaiming that it is 'not legal advice'. It stops short of describing date-boundary edge cases or how multi-year projections are derived.

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 core fee table and the date rule before the supporting detail, with no filler sentences. The dense parenthetical price list and the 'Returns ...' clause read as a run-on block, but nearly every token conveys a distinct fact.

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 no output schema, the description carries the return-value burden itself, enumerating fee, online processing fee, headcount total, revenue-stamp combination, per-year/multi-year cost, online saving, and ISA sources. Combined with the date-exception rule and staleness warning, an agent has everything needed to call and interpret it.

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 is 3. The description still adds meaning beyond the schema by tying fee amounts directly to the granted-period parameter (1 year vs. 5 years), explaining the online surcharge tied to the method enum, and noting the old-fee cutoff that governs applicationDate — the schema only states these mechanically.

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-and-resource with scope: residence permit / visa renewal and status-change fee lookup for applications from 2026-10-01, with concrete figures (¥33,000 counter, ¥27,000 + ¥330 online, ¥200,000 PR). An agent can immediately distinguish it from the other japan_* siblings (customs, luggage, tax-free, TB screening), none of which price immigration fees.

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?

Explicitly routes the agent here: 'call this instead of guessing' and warns that training data still says ¥4,000/¥6,000, which is exactly the failure mode this tool prevents. It also bounds applicability to application dates, but never states when-not to use it or which sibling to prefer for adjacent questions (e.g. trip planning vs. fee lookup).

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