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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds genuine behavioral detail: how the query is parsed, that abbreviations work for regions, and that the interpretation is echoed in `interpreted` — non-obvious output behavior. No rate limits or ordering details.

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 with purpose, then examples, then parsing semantics, then the routing cue. The bilingual duplication is deliberate for the audience, though it roughly doubles the text without adding new semantics.

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?

For a two-parameter search with no output schema, the description supplies the parsing contract and flags the `interpreted` echo field, which is what an agent most needs to trust results. Missing result ordering, pagination beyond `limit`, and returned-field shape, but the essentials are present.

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 baseline is 3. The description exceeds that by explaining the parsing model of `query` — a region word is read as an administrative area (abbreviations accepted) and the remainder is matched against record content and dataset names. `limit` is left to the schema, which documents it adequately.

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 ('Find') and resource ('Korean public-data records') scoped by region and topic, with concrete examples (Gangneung libraries, Jeju tourism). It is distinguishable from catalog-style siblings, but never names them, so an agent must infer the boundary against search_catalog/list_datasets.

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?

'Use it for what-is-where questions' gives an implied usage context, and the examples hint at region+topic phrasing. However, with nine siblings including search_catalog and list_regions, no explicit when-not or alternative routing is provided.

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