refine_seoul_recommendations

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

With no annotations, the description carries the burden and it states the core behavior: it operates only on the previous results and does not perform a new search, saving tokens and API calls. It could add more about output form or how filters combine, but the main non-side-effect behavior is disclosed.

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?

Single concise sentence front-loads the action and includes the main benefit. There is no redundant text or repetition of schema fields.

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 straightforward refinement tool with fully documented parameters, the description plus schema is sufficient for an agent to call it. It does not describe the output structure, but the output is implied to be the same shape as the input recommendations; with no output schema, a slightly more explicit return note would push this to 5.

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 the baseline is 3. The description adds only the generic notion of filtering/sorting by conditions; individual parameter meanings are left to the schema. No additional semantics or examples are given in the description.

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?

Description uses a specific verb, re-filter/re-order, and a clear resource, previous recommendation results, and explicitly states it does not re-search. This differentiates it from sibling tools like recommend_seoul_apis_for_idea and search_seoul_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?

The description conveys the context for use, i.e., after a recommendation has been made, to narrow/re-sort without incurring a new search or API call. It does not explicitly name alternatives or exclusion conditions, but '재검색 없이' makes the when-to-use scenario clear.

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