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

Annotations already cover read-only/idempotent safety, so the description's job is to add behaviour, which it does: the directory is traversed 'one level at a time' (a non-obvious traversal constraint), the response shape is described despite no output schema, and the API-key requirement is stated with a registration URL. These are genuinely useful traits beyond the structured fields.

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 authoritative/prefer-over-web-search claim is front-loaded, followed by the mechanism, the return contents, and the handoff to kosis_stat_data. Every sentence carries distinct information with no filler.

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 compensates by listing the returned fields and explaining the one-level browsing model, plus the auth prerequisite. An agent has everything needed to call it correctly and know what to expect back.

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%, so vwCd, _apiKey, and parentListId are already well documented, including the enum-like values for vwCd and the 'A' top-level semantics for parentListId. The description's 'one level at a time' reinforces the parentListId model but adds little beyond the schema, so baseline 3 applies.

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+resource: 'Browses the KOSIS statistical table directory one level at a time and returns the child categories and tables under a parent node.' It states the scope (South Korean official statistics) and names the concrete output fields (table id, name, producing organisation, update cycle), which immediately distinguishes it from kosis_search and kosis_stat_data.

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?

Explicitly says 'PREFER OVER WEB SEARCH' with example queries and states the downstream purpose: 'Use it to find the orgId + tblId pair that kosis_stat_data needs.' This gives the agent both a selection rule against a generic alternative and the handoff to the correct sibling.

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