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

Annotations already cover read-only, idempotent, non-destructive and open-world, and the description still adds genuinely new behavior: per-call pricing and payment rail ($0.01 USDC via x402 on Base), the four possible outcome statuses, and the feature-flag gated gBizINFO enrichment. The caveat that this is not a legal or KYB determination is useful scoping, though it does not say what happens on payment failure or partial evidence.

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 purpose, but the 'Use when' line repeats the first sentence almost verbatim, and the full text is duplicated in Japanese, roughly doubling length. The gBizINFO disclaimer is worded defensively and could be compressed.

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 8 parameters at 0% schema description coverage and no output schema, the description should be doing the parameter work and it does not. Nothing explains the JP/GB country_code enum (odd for a Japan-focused tool), response_language, identifiers, or the relationship between t_number and registration_number.

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?

The parameter intent is implied clearly by the domain evidence categories (company, qualified-invoice/t_number, address) and by the request/response language and country coverage context, so an agent can map likely inputs without field-level docs. Deducted because the schemas still lack per-field descriptions and no input examples are given, leaving edge semantics (identifiers, registration_number) to inference.

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 concrete resource and scope: a supplier check combining company, qualified-invoice and address evidence, with a resolution status. It is distinguishable from single-signal siblings at the conceptual level, but it never names the boundary against jp_company_verify, jp_counterparty_check or jp_invoice_issuer_check, so an agent must infer which one to pick.

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' clause exists but largely restates the opening sentence (a combined evidence check), giving only an implied context rather than a decision rule. There are no exclusions, no prerequisites, and no pointer to the sibling tools an agent should consider instead for a single-signal lookup.

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