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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false, so the safety profile is covered; the description goes further by disclosing that calls are paid ($0.03 default, $0.10 with enrich) in USDC via x402 on Base, and that only successful calls are charged. It also discloses the verification boundary of the output, which no annotation conveys. This is exactly the kind of non-obvious operational context the description should carry.

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 front-loaded with purpose, then when-to-use, then return scope, then price — a sensible order with no filler. The full Japanese mirror doubles the length, which is defensible for a Japan-focused service but does add bulk without new information for an English-reading agent.

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?

For a 10-parameter, paid, no-output-schema tool the description covers cost, output scope, input modality, and the enrich trade-off, which is most of what an agent needs. The notable gap is that zero parameters are required, yet the description never states that at least one of front image, back image, or Base64 must be supplied, nor how conflicting image sources are handled.

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 70%, and front_image_url/back_image_url/max_pages carry no schema description at all; the description compensates by stating the tool accepts a front/back HTTPS image URL or a small Base64 payload. It also ties enrich=true to a registry pre-check of the organization, though the schema's own enrich description already states the same rule and the costs, so part of this is duplication rather than added meaning.

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 opens with a concrete verb and resource plus the accepted input modalities: 'Read a Japanese business card (front/back HTTPS image URL or small Base64)'. It also delimits scope by stating what is excluded ('no corporate-number or NTA issuer verification'), which separates it in practice from jp_company_verify and the invoice-registry siblings. It stops short of naming those siblings, so an agent must infer the routing rather than read it.

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?

An explicit 'Use when' clause enumerates the exact fields that should trigger this tool (person, role, department, company, phone, email, address). The 'Returns ... no corporate-number or NTA issuer verification' line acts as an implicit exclusion toward the verification siblings. An explicit 'if you also need registry/NTA verification, use jp_company_verify' statement is the only missing piece.

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