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

Goes well beyond the annotations by disclosing per-call price ($0.03 USDC via x402 on Base), the external NTA registry verification step, and that returned validation is deterministic with field status and review signals. It does not say what happens when a T-number fails registry lookup or how errors/partial OCR are reported, which keeps it from a 5.

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?

The English text is well front-loaded with labeled 'Use when:', 'Returns:', 'Price:' blocks and zero filler. However, the entire description is then duplicated verbatim in Japanese, roughly doubling token cost for an agent that only needs one rendering.

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 compensates by enumerating return contents (structured fields, deterministic validation, field status, review signals) and discloses cost and validation limits. For a 7-parameter, multi-source-input tool it is nearly complete, missing only failure-mode behavior.

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 one-of input source rule, page limit, size ceiling and language enum are already fully documented in the schema. The description adds only indirect meaning (that T-number checks relate to registration fields) and no syntax or format detail beyond what the schema provides; baseline 3 applies.

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 ('OCR a Japanese receipt') plus the validation scope (local amount, tax, T-number, NTA registry lookup), which is enough to separate it from jp_business_card_extract or jp_address_validate. It never explicitly contrasts itself with the adjacent jp_invoice_extract / jp_invoice_extract_and_verify siblings, so an agent must infer the receipt-vs-invoice boundary from the noun alone.

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?

The 'Use when:' line gives a clear triggering context (Japanese receipt/領収書 OCR with tax, amount, T-number and format checks), repeated in Japanese for the same audience. There are no explicit exclusions or 'use X instead' routing to the invoice/verification siblings, so it stops short of full when-not guidance.

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