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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior. The description adds meaningful context beyond them: rules are deterministic and dated, and the output is explicitly 'not tax advice'. It does not describe return format or error behavior, but with this annotation coverage the added domain caveats are the right contribution.

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 tool's core computation, then a compact caveat sentence. Dense but every clause (threshold, caps, deadline, regime, anti-hallucination warning) earns its place with no filler.

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 the full decision surface an agent needs — eligibility, refund cap, deadline, and old-vs-new regime selection — for a read-only tool with no output schema, so return-format detail is not required.

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 adds genuine meaning: the ¥5,000 tax-exclusive per-store/day eligibility threshold, the 10%/8% refund caps, and the per-store/day grouping that governs the receipts array — content not fully present in 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?

States a specific verb+resource with precise scope: computing Japan tourist tax-free refund eligibility under the 2026-11-01 regime, listing per store/day eligibility, refund caps, 90-day deadline, and regime selection. An agent can distinguish it immediately from japan_customs_allowance_check and japan_dual_pricing_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?

Gives clear context for use and an explicit directive ('call this instead of guessing', because training data describes the obsolete old system). It also frames regime selection by purchase date, though it does not explicitly name sibling tools or exclusion conditions.

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