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

Annotations already indicate read-only, idempotent, and open-world behavior. The description adds valuable context: it combines two government APIs, returns combined results, and notes that registered=false is expected under Japanese tax law. This goes beyond what annotations provide and helps set agent expectations.

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 description is concise and well-structured: a clear English purpose statement, a Japanese version for native speakers, a usage trigger sentence, and a behavioral note. Every sentence serves a purpose. No unnecessary words.

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 tool with annotations covering safety and idempotency, and an output schema (not shown but exists), the description provides sufficient context: it explains the composite nature, the expected input format, the combined output (invoice + corporate), and a domain-specific nuance about government responses. No gaps.

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 input schema has one parameter with full description coverage (100%), including format and example in Japanese. The description repeats the format (T+13 digits) but does not add new semantic meaning beyond what the schema already provides. Baseline 3 is appropriate given high schema coverage.

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 clearly identifies the tool as a one-call composite that returns both invoice registration status and corporate details from a T-number. It uses specific language ('T-number (T + 13 digits)', 'invoice registration status', 'corporate details') and distinguishes itself from siblings like invoice.validate or houjin.lookup by being a combined call.

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 description explicitly states when to use the tool: when an AI agent receives a T-number and needs to validate both invoice compliance and company identity in one step. It also provides a caveat about government agencies returning registered=false. While it doesn't explicitly mention when not to use or alternatives, the context is clear and actionable.

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