na_collect

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

Beyond the annotations, the description adds rich behavioral context: it writes files to disk (formats, save=false preview mode, out_dir default), discloses the '|' means AND operator quirk, exposes the 99,000-record retrieval limit, and explains that cap_hit_terms/incomplete_terms in return metadata signal incomplete data. This complements the openWorldHint annotation with concrete completeness caveats — exactly the context structured fields cannot convey.

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 description is long but information-dense and well-sectioned: purpose first, then terms semantics, the warning block (marked with ⚠️), formatting/output defaults, and return metadata. Every sentence carries operational value given the 14-parameter surface and zero schema coverage; it could be slightly tightened, but the structure earns its length.

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 complex tool with no output schema and no parameter descriptions, it covers the critical operational aspects: aggregation semantics, parameter defaults, the local-vs-server filtering pitfall, and the meaning of return metadata fields. Minor gaps remain for name, page_size, max_records, and extra_params, which are left undocumented at 0% coverage.

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?

With 0% schema coverage, the description carries the full burden and succeeds: it defines the terms format with an example list, the search single-term alternative, formats allowed values (xlsx/csv/json/sqlite), save=false preview behavior, out_dir default (home na-output/), and the option='발행년도,2000|발행년도,2010' syntax for server-side filtering. Roughly 10 of 14 parameters receive meaningful semantic detail beyond their bare names.

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?

The description opens with '[수집]' and states it queries each search term, aggregates them as a union, and saves to file. This specific verb+resource clearly differentiates it from siblings like na_search, na_detail, and na_status. The union (OR) semantics plus a concrete example make its function unambiguous.

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 gives clear context: use `terms` for multiple searches merged by union, `search` for a single term instead of terms, and it explains the OR-vs-AND operator quirk with an example. It also warns when NOT to rely on year_from/year_to (local post-processing only) and directs users to `option` with `dbname` for server-side year filtering. However, it never names sibling tools as alternatives (e.g., when to prefer na_search), so exclusions remain implicit.

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