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

Annotations already cover the safety profile (readOnly, idempotent, closed-world), but the description adds substantial behavior beyond them: it lists the input variants it absorbs (full/half-width, spacing, kanji vs. arabic numerals, ヶ/ケ, omitted county names), the prefecture inference rule when the city is unique, and explicit limitations (no block-level verification, no coordinates). That is exactly the kind of expectation-setting an agent needs.

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: the first clause states the operation and its output before caveats. The bilingual duplication roughly doubles the length, but the Japanese text plausibly serves the target audience rather than being filler, so the cost is modest. Every clause carries 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?

There is no output schema, so the description must carry return semantics — it does, naming the four-part split and the postal-code candidates, and it flags the two key limitations. It could be slightly more precise about the shape/count of returned candidates, but for a single-input, single-purpose tool this is close to complete.

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 the schema already supplies an example, so the baseline would be 3. The description still adds value by characterizing the input domain — a free-form Japanese address tolerant of width, spacing, numeral and orthography variants — which tells the agent it can pass raw user-typed text without pre-cleaning.

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 (split/normalize) and resource (Japanese address), and names the exact decomposition it produces (prefecture, city, town, rest) plus the postal-code candidates it returns. This is clearly distinguishable from siblings like lookup_postal_code and search_postal_code, which start from a postal code rather than a raw address.

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 implies the use case (you have a messy Japanese address that needs parsing) and draws a useful boundary by stating it does NOT verify block/house numbers and returns no coordinates. However, it never names an alternative or says when to prefer this over lookup_postal_code, which overlaps on the postal-code-candidate output. Usage is inferable but not guided.

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