Maison de Talents

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so safety and repeatability are covered without the text. The description adds the scope of the returned detail fields, but says nothing about auth requirements, rate limits, or error behavior when an id does not exist.

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?

Two short sentences with the action and the source of the id front-loaded, and the Korean/English pair is compact. The bracketed promotional prefix is extraneous content that does not earn 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 single-parameter read tool with no output schema and annotations covering the safety profile, the description is nearly sufficient: it names the return contents and the id source. Missing only failure-mode behavior (invalid or expired posting id) to be fully complete.

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% and the single parameter is documented in the schema as 'search_jobs 결과의 공고 id', including a UUID format and pattern. The description only restates that same provenance, so it adds no format, constraint, or edge-case meaning beyond the schema.

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 and resource ('공고 id 의 상세를 가져옵니다' / 'Get details of a job posting by id') and enumerates what the detail contains (자격요건·근무조건·급여·마감일). It partially separates itself from the sibling search_jobs by framing itself as the detail lookup for ids found there, though the leading bracketed campaign tag '[메종 드 탤런트 명품 매장 채용]' is noise that muddies the statement.

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?

Clearly establishes the prerequisite that the id comes from a search_jobs result, which tells an agent the correct call order. It offers no explicit exclusions or comparison against get_salary_benchmark, so it is clear context rather than full when/when-not routing.

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 cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds genuinely useful behavioral context beyond them: the return units are 만원 and the basis is annual salary (연봉 기준), and it discloses that omitting experience returns all ranges (생략 시 전 구간).

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 the core purpose, then the enum glossary. The Korean and English sentences are somewhat redundant, but the enum definitions each carry information, so there is little waste overall.

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 and only two parameters, the description supplies what an agent needs: scope, filterable dimensions, enum meanings, and the unit/basis of returned values (만원, annual). The precise return structure is unspecified, which is a minor 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?

Although schema coverage is 100%, the schema only labels the enums tersely ("업종 코드", "경력 코드"). The description explicitly expands every enum value (luxury=럭셔리 패션 … lifestyle=라이프스타일; entry=신입(0년) … lead=10년+), adding real meaning the schema lacks.

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: 조회 (lookup) of 연봉 벤치마크 (salary benchmarks) by 업종·경력 for Korean luxury retail staff. It is clearly distinct in resource from siblings get_job/search_jobs, though it never names those siblings explicitly to route the agent.

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?

Usage is implied by the domain (query compensation data for a category), but there is no explicit when-to-use, when-not-to-use, or reference to the sibling tools get_job/search_jobs. An agent can infer the intent but receives no routing guidance.

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, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds domain scope and notes the args are optional (already implied by the 0 required params) but says nothing about result count behavior beyond limit, pagination, or freshness – adequate but not rich.

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 the domain and the search action, then a bilingual restatement plus examples. The KO/EN duplication and trailing 'all arguments are optional' note are mildly redundant but the whole thing stays compact and readable.

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 4-param read-only search with full schema coverage, the description gives enough domain context to invoke correctly. It omits return-shape/ordering expectations, but with no output schema and exhaustive parameter docs this is a minor gap rather than a blocking one.

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 each of the four parameters (brand, query, region, limit) is already documented with examples in the schema. The description only alludes to job types generally and adds no syntax, format, or matching-semantics detail 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?

States a specific verb (검색/search) and resource (active retail job postings) with concrete scope – luxury boutiques, department stores, duty-free in Korea – and lists example roles/brands. It implies but never names the sibling tools (get_job, get_salary_benchmark), so differentiation is left to inference from the narrow domain.

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?

Usage is implied: the agent understands it should call this to find postings, and it notes all arguments are optional. But there is no explicit guidance on when to prefer this over get_job or get_salary_benchmark, no filter-combination advice, and no exclusions.

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