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

Annotations already cover readOnly, idempotent and non-destructive; the description goes beyond them by disclosing the paid-call model ($0.01 USDC per successful call via x402 on Base) and the input ceilings (small Base64, max 1–2 PDF pages). What it does not disclose is failure behavior (e.g. what happens on an unreadable scan or when payment fails), which for a paid OCR call would matter.

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 block is well front-loaded (purpose, when-to-use, returns, price), but the entire description is then repeated verbatim in Japanese, roughly doubling length with no added information for an agent that already read the first half. Every sentence earns its place in the English block; the mirrored block does not.

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 and does so at a category level (invoice fields plus format, arithmetic, tax, completeness, review status). Combined with the fully described 7-parameter schema and the paid-call disclosure, this is nearly complete; only concrete output shape or error semantics are absent.

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% and every parameter already carries bilingual descriptions, so the baseline is 3. The description adds only a coarse restatement of the three input modes ('text, HTTPS file URL, or small Base64') with no new syntax or selection rules beyond what the schema states.

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 ('OCR a Japanese billing invoice') plus the exact validation scope (local date, tax, arithmetic, T-number checks) and the explicit negative scope ('no registry lookup'). That negative scope separates it cleanly from siblings like jp_invoice_extract_and_verify, jp_invoice_issuer_check and jp_receipt_extract without opening any schema.

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?

A 'Use when' clause names the situation: Japanese billing-invoice OCR with deterministic quality checks and no registry lookup. The exclusion of registry lookup implicitly routes verification needs to a sibling, though it never names that alternative, so the agent must infer it from the sibling list.

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