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

Annotations cover safety (readOnly, idempotent, closed-world), and the description adds substantial context beyond them: which input variants it absorbs (full/half-width, spacing, kanji vs. arabic numerals, ヶ/ケ, omitted county names), that it does not verify block numbers and returns no coordinates, the meaning of `level` 0-3, nullability below level 2, and the `partial`/`ambiguous` flags.

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?

Purpose is front-loaded, followed by behavior, level semantics, then flags in a logical order. The bilingual English/Japanese rendering roughly doubles the length, and the Japanese portion drops some details (flags, city_candidates note), so there is mild redundancy rather than pure waste.

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 no output schema, the description correctly carries the burden of explaining return values: `level`, `city_candidates`, `postal_codes`, `address`, `municipality_code`, and the flags. For a single-parameter tool, an agent has everything needed to call and interpret it.

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% and there is only one parameter, so the baseline is 3. The description adds genuine input semantics beyond the schema example by explaining the tolerated input variation (full/half-width, spacing, numeral styles) and the prefecture-fill behavior, which helps the agent format input.

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 ('Split a Japanese address into prefecture, city, town and the rest') and defines the exact scope ('to town level'). The tool is clearly distinguishable from siblings like lookup_postal_code by its parsing/decomposition behavior, and it explicitly declares its boundaries ('Does NOT verify block/house numbers and has no 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?

Usage is implied rather than stated: the agent learns it handles messy/omitted address forms and should ask the user or show all candidates when `ambiguous`. However, it never says when to prefer this over lookup_postal_code or search_postal_code, so alternative selection is left to inference.

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