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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds valuable behavioral details: returns canonical form, structured components, postal code, coordinates, match level, confidence, and mandatory attribution. No contradiction with annotations.

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 consists of three concise sentences. The first states the primary action and source, the second lists return components, and the third provides usage context. No unnecessary words; all content earns its place.

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?

Given a single parameter, no output schema, but annotations cover safety and idempotency, the description fully explains the return structure (canonical form, components, postal code, coordinates, match level, confidence, attribution) and usage context. Complete for agent decision-making.

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% with a single parameter 'address' described as 'A raw Japanese address string (may include postal code, building, floor)'. The tool description adds context about normalizing against ABR but does not significantly enhance parameter meaning beyond the schema. Baseline 3 is appropriate.

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 states the verb 'Normalize' and the resource 'free-form Japanese address against the official Address Base Registry'. It distinguishes from siblings which deal with corporations, calendars, and name splitting, making purpose unambiguous.

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 'Useful when an AI agent must clean or de-duplicate Japanese B2B/customer records', providing clear context for use. It does not explicitly mention when not to use, but the sibling tools are sufficiently different to avoid confusion.

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