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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds information annotations cannot carry: the response status set, the confidence/scope/reason fields, and the pricing model ($0.005 USDC per successful call via x402 on Base), which is a real cost/authorization consideration.

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 portion is reasonably front-loaded: purpose, use case, return values, price. But the entire block is duplicated verbatim in Japanese, roughly doubling length for the same content, and the parameter names are never mapped explicitly to the input fields.

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 6-parameter, zero-required, evidence-merging tool with no output schema, the description does explain the return statuses and what signals come back. However, it is incomplete on inputs: an agent cannot tell from description or schema what shape 'postal_evidence'/'geocode_evidence' objects take, what 'strict' changes, or how 'required_level' (1-8) affects the verdict.

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 0% across 6 parameters, so the description carries the full burden. It only alludes to three inputs (parsed address, postal evidence, geocode evidence) and says nothing about 'address', 'strict', or 'required_level' (an integer capped at 8), leaving the most confusing parameters unexplained.

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 (validate a Japanese address) plus the evidence sources it combines (parser, postal, geocoder) and the outcome taxonomy (exact/partial/ambiguous/conflict/unverified). It never names or contrasts with jp_address_normalize or other siblings, so differentiation is left to the agent.

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 gives one positive trigger: needing a single evidence-based quality decision combining the three evidence types. There is no 'do not use when', no routing to jp_address_normalize for plain normalization, and no guidance on when partial evidence inputs are acceptable.

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