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

Annotations already declare readOnly, idempotent, non-destructive, open-world behavior; the description adds the meaningful extra that results come from the JPO public register and are legal-status snapshots. It does not discuss latency, coverage gaps, or what happens on an unmatched number, so it stops short of full transparency.

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 purpose, then a field list, then provenance, then input examples — each element earns its place with no filler or repetition of annotation data.

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 an output schema present and annotations covering safety, the description only needs to convey scope and provenance, which it does. Minor missing pieces: behavior on unknown numbers and the legal-status vocabulary boundaries (e.g., appeal/invalidation stages) are not addressed.

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%: both `number` (formats, accepted prefixes like 特願) and the `number_type` enum with default are fully documented in the schema. The description's examples largely repeat that, so the baseline of 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 and resource ('look up a Japanese patent or utility model by number') and immediately enumerates the returned fields (stage, latest event, numbers/dates, title, applicant, FI classifications). This clearly separates it from the sibling jp_trademark_status, which covers a different IP right.

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?

Gives concrete input examples ('2020-000001', '6770223') and names the authority of record (JPO public register), which tells the agent what kinds of numbers this tool accepts. It does not explicitly state when to prefer this over jp_trademark_status or what to do if the number is unknown, so a small gap remains.

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