address_normalize

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

Annotations already declare readOnlyHint and openWorldHint, and the description adds specific behavioral details: it fixes character width variants and old-form kanji, resolves postal codes, and returns a 0-1 confidence score. This goes beyond the annotations and provides useful expectations about the transformation and output, though it omits any failure behavior.

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 two sentences, front-loaded with the primary action and output, and the second sentence states the return value. There is no redundancy or filler; every word adds information.

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 the tool has one parameter, no output schema, and rich annotations, the description covers the core behavior and return value. It is adequate for a read-only normalization tool, though it could possibly mention what happens on invalid input, but that is not necessary for basic use.

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 100%: the single parameter 'address' is already described as 'A Japanese address string, any common notation.' The description adds context about normalization (e.g., fixing width) but does not add new parameter-level details, so the baseline of 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 uses a specific verb 'Normalize' with a clear resource ('a Japanese address') and states the output components (prefecture/city/town/chome) and key transformations (fixing fullwidth/halfwidth and old-form kanji, resolving postal code). This distinguishes it from sibling tools like address_parse or address_geocode, which focus on parsing or coordinates.

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 clearly implies the tool is for normalizing Japanese addresses into clean components, which gives context for when to use it. However, it does not explicitly mention alternatives or when not to use this tool, leaving some ambiguity given the many sibling address-related tools.

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