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

No annotations are supplied, so the description carries the full burden. It adds real domain behavior — wages are KRW interpreted jointly with wage_type, and undisclosed wages surface as wage_type='협의' — plus a post-call obligation to cite page_url/url. It omits pagination/result-size behavior, ordering, and any explicit statement that this is a read-only operation.

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?

Four short sentences: purpose, filter scope, wage semantics, then the page_url attribution instruction — front-loaded and free of padding. The final attribution sentence is somewhat operational rather than definitional but still earns its place for correct output handling.

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 six-parameter search tool with no output schema and no annotations, the description covers purpose, filter scope, value interpretation, and the shape of the response link (page_url / per-item url). Remaining gaps — pagination, default limit, ordering — are minor for a filtered list tool.

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 coverage is 67%, and the description compensates well for the gap by explaining the unit and coupling of wage_min/wage_type and decoding the '협의' enum value, which the schema leaves undocumented. It does not address limit bounds or the include_closed default, but the highest-ambiguity parameters are covered 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?

The description opens with a specific verb + resource ('구조화된 제주 채용 공고를 필터로 검색합니다') and immediately names the filter dimensions, so an agent knows this is a filtered search over Jeju job listings. It is clearly distinct in substance from search_posts or the job-listing write tools, though it never explicitly differentiates itself from those siblings by name.

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 filter list ('지역·직종·급여 필터 지원') and the closing instruction to surface page_url to the user, but there is no explicit when-to-use/when-not guidance, no mention of alternatives such as search_posts, and no note on defaults like include_closed=false driving result choice.

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