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.

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

Beyond the readOnlyHint/openWorldHint annotations, it discloses measured operational traits: the returned field set is identical to na_search (redundancy), each call consumes daily quota (10,000/day), nonexistent control numbers still return ERR04 making them indistinguishable from transient errors, and access requires a separate data.go.kr application. This is exactly the class of behavioral context annotations cannot carry.

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?

Although longer than typical descriptions, every sentence earns its place: purpose is front-loaded, the critical redundancy caveat follows immediately, then error and auth warnings. Structured formatting (bold, emoji markers, bullet separations) makes the dense content scannable, and there is no filler or repetition.

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 single-parameter read-only lookup with no output schema and minimal annotations, the description is complete: purpose, parameter origin, output equivalence (which doubles as return-value documentation since fields mirror na_search), error semantics, quota impact, and access prerequisites are all covered. The empirical field-count breakdown per document type reinforces the redundancy claim without leaving gaps.

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 description coverage, the description fully compensates: it defines controlno as the control number taken from na_search results and supplies two concrete format examples (MONO12026000012887, KINX2026037525). This gives the agent both the provenance and the shape of the only parameter.

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 opening line states a specific verb and resource: '제어번호 1건의 서지정보를 조회한다' (retrieves bibliographic information for one control number). It further distinguishes from siblings by asserting the field set is empirically identical to na_search's raw output, while na_toc is named as the tool that returns genuinely new content.

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 is exemplary on this dimension: explicit when-to-use ('쓸 자리는 제어번호만 아는 자료를 조회할 때'), explicit when-not-to-use ('이미 검색한 자료라면 이 도구를 부를 이유가 없다'), and a named alternative for a specific need (na_toc for table-of-contents text). No inference is required from the agent.

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

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

The annotations already declare readOnlyHint=true and openWorldHint=true, covering the safety profile. The description adds valuable context that the values are 'actually accepted' and backed by 'measured evidence,' indicating empirical verification rather than mere documentation.

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 a single compact sentence that front-loads the core value proposition: a list of working values plus the empirical basis. It contains no filler and does not repeat information already present in annotations or schema.

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 parameterless, read-only metadata tool, the description adequately conveys what the tool returns and why it is reliable. The lack of a response format is acceptable given the tool's simplicity and supporting annotations.

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?

The tool has zero parameters, so the schema trivially covers all parameters and the description need not add parameter-level semantics. The baseline of 4 applies because there are no parameters to explain.

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 identifies the tool as a reference list of values actually accepted by the API, with examples like search items and dbname, making its purpose as a metadata/inspection tool clear. It lacks an explicit verb and does not contrast with sibling tools, but the resource and intent are 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 implies the tool should be used to discover which field values and dbnames are valid for this API, which is a natural prerequisite for search/detail calls. However, it does not explicitly state when to use this tool over alternatives or provide any exclusions.

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

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

Beyond the readOnlyHint and openWorldHint annotations, the description discloses critical behaviors: invalid search-field values silently return the entire 13,097,591-record catalog, dbname mismatches fail with ERR04, and the API caps retrieval at 99,000 records via pageno 99 and page_size 1000. It also explains cap_hit and truncated semantics.

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?

Although long, the description is densely informative and well-structured: purpose first, then search syntax, field whitelist, dbname behavior, option syntax, paging, and limits. Warnings and examples are placed exactly where confusion would occur, and no sentence is 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?

The description covers nearly every operational constraint needed to invoke this complex tool correctly, including validation behavior, pagination limits, and response flags. It falls slightly short by not describing extra_params and not summarizing the general result shape, especially since there is no output schema.

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 description coverage, this description fully compensates for search, dbname, option, page_size, and max_records, including required formats, allowed values, defaults, and failure modes. The only gap is extra_params, which appears in the schema but is never explained 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?

The first sentence names a specific action and resource: searching the National Assembly Library catalog DB for books, theses, and articles. It further distinguishes this tool from siblings by explicitly routing OR needs to na_collect and field-vocabulary checks to na_fields.

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 explicit when-to-use guidance: use na_collect when OR semantics are needed, use na_fields to confirm valid field names for detailed search, and use dbname to switch to detailed search. It also explains what happens if the documented format is not followed.

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

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is known. The description adds useful behavioral context: it discloses that the tool performs an actual network round trip and verifies authentication-key possession. This goes beyond the annotations, though it stops short of explaining failure modes or side effects like potential latency.

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 a single front-loaded sentence that conveys the core purpose and key behavioral nuance without any filler. Every token earns its place.

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 zero-parameter health check this is mostly adequate: the agent knows what is checked and that a network call occurs. However, there is no output schema and the description does not indicate what the response looks like or how to interpret the result, leaving a notable gap.

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?

The tool has zero parameters, so the empty schema fully covers all parameters. The description does not need to explain parameter meanings; the baseline of 4 applies because no parameter ambiguity exists.

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 states a specific action — 'connection check' — with concrete scope: whether an authentication key is held and one actual round trip to the data-search API. This clearly distinguishes it from sibling data-retrieval tools like na_search or na_detail.

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 implies usage as a connectivity/health check before other API calls, but it does not explicitly state when to use it versus alternatives, nor does it mention any exclusions. The purpose is clear enough to infer the context, but no direct guidance is provided.

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

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

The description adds substantial behavior beyond the annotations: it explains that the raw HTML is escaped, that the tool unescapes and converts it to newline text, that the main delimiter is '<p>', and that hierarchy is preserved via line indentation. It also documents the no-TOC case as normal. The readOnlyHint/openWorldHint annotations are consistent and this context enriches them significantly.

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 well-structured: purpose first, then parameter meaning, then usage warnings presented as clear bullet-like lines. Every sentence earns its place, but the ambiguous phrase '다음 자료종은' promises a list of excluded material types that is not actually enumerated, slightly weakening the structure.

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 simple one-parameter read tool with no output schema, the description covers the input source, output transformation, empty-result behavior, and quota-aware usage guidance. The main gap is the unspecified list of material types that all have TOC='N', which leaves part of the exclusion advice incomplete.

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 description coverage, the description compensates by explaining that 'controlno' is the control number from search results ('검색 결과의 제어번호'). This adds meaningful sourcing context beyond the bare schema. It does not include example formats, but with a single string parameter this is adequate.

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 states a specific verb and resource: it retrieves table-of-contents information for one control number ('제어번호 1건의 목차정보를 조회한다'). The [목차] prefix and the scope make the purpose unambiguous, though it does not explicitly differentiate itself from sibling tools like na_detail or na_fields.

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 selection criteria: call this tool only when the search result's '목차' field is 'Y', and warns that records without TOC are normal. It also notes that certain material types have all 'N' values and should not be called. It does not name alternative tools, so it stops short of full when-to-use-versus-alternatives guidance.

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