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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds real context beyond them: the dated authority set (10_00240, 16-2, 2026-10-01 fee table), the 'always' rules (part-time ends at graduation, 14-day school report), and the educational/not-legal-advice disclaimer. It does not say how invalid or inconsistent inputs (e.g. an appliedDate already in the past) are handled, so it stops short of full behavioral disclosure.

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?

Purpose and the 'Use for' triggers are front-loaded, which is good, but the body is a single run-on block of parenthesised clauses and pipe separators where the plan branches, the always-rules, and the 18-field return list all blur together. Nearly every clause carries information, so little is padding, but the lack of any structural separation makes it harder to parse than its length warrants.

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, no output schema, and multi-branch logic, the description carries a lot of weight and does so: it enumerates the returned fields and verdict values (too_early | open | urgent | applied | not_eligible | expired | info), the branch rules, the always-applicable deadlines, sources, and disclaimer. An agent could call it correctly and interpret the result without further documentation.

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, and most of what the description says about inputs (jobStartDate needed for job_offer, 内定者 rules, April December–January filing) restates or expands the enum/default documentation already present. The one genuine addition is the eligibility link 'language-school grads only with foreignBachelor', which explains a parameter dependency not spelled out in the schema — useful but a small increment over a fully documented 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 states a specific verb+resource combination (dated checklist for an international student graduating in Japan changing 留学 to a work/job-hunting status) and enumerates the four plan branches it handles. Trigger queries such as 'when to change student visa to work visa Japan' and '留学 就労ビザ 変更 いつから' make the intended scope unmistakable, and the part-time/14-day items further distinguish it from the renewal and job-loss siblings.

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 conveyed through the plan enum explanations and the quoted example queries, which tell the agent exactly which question shapes route here. There is no explicit when-not guidance or hand-off note, even though 'can I work part-time after graduation in Japan' arguably belongs with japan_parttime_work_check — that boundary is left implicit.

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