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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world, so the safety profile is covered. The description adds genuinely useful traits beyond that: normalization of province names to official forms, handling of 일반구, leading postal codes, and no-space addresses. It does not disclose what happens with unparseable or non-Korean input, which matters for a batch tool.

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?

Two tight sentences: outputs first, edge-case handling second, then a one-clause caveat. No filler and the most important information (what it returns) is front-loaded.

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 does a good job naming the four returned components, but it never states the response shape (object per address, parallel arrays, error entries) or behavior on failed parses. For a batch-of-up-to-1000 tool, that leaves a real gap an agent must discover by calling 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?

There is a single parameter with 100% schema coverage, and the description adds nothing about the parameter itself beyond what the schema states ('Up to 1000 addresses'). Baseline 3 is appropriate; the batching limit and partial-failure semantics are left to the schema.

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?

Uses a specific verb ('split') on a specific resource (South Korean addresses) and enumerates the four output components with Korean terminology (시도, 시군구, base address, detail). An agent can distinguish it from the sibling kr_name_split purely from the text.

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 context is clear: parse raw Korean address strings into structured parts. The caveat 'Rule-based; does not look up a database' implicitly sets an exclusion (do not rely on it for verified/authoritative address validation), but there is no explicit statement of when to prefer a sibling or an alternative approach.

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