search

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

With zero annotations, the description carries the full burden and exceeds it: it discloses the fusion internals, automatic application of a token-default project, down-ranking of other-project notes with an 'other-project' marker on matched, expansion of neighbor chunks into context, and the latency/cost tradeoff of rerank. Return shape is stated. This is exemplary behavioral disclosure for a search tool.

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?

There is no filler and the core purpose is front-loaded. But the description is a dense continuous Korean block: the 'other-project' warning interrupts the parameter walk-through, and the project/note explanation is convoluted enough that list formatting or line breaks would improve scannability. Efficient but verging on information overload.

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 6-parameter hybrid search tool with an output schema present, nearly all decision-critical context is covered: the scope gotcha, cross-project cause-mismatch warning, rerank cost, expand behavior, and return format. Minor gaps remain: no error/no-result behavior, no limit ceiling or pagination note, and the meaning of '토큰에 기본 프로젝트' is stated but not precisely defined.

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 0%, so the description must compensate — and it does. It supplies the source enum values the schema omits, explains project scoping semantics and the note result's project field (null = team-wide), and clarifies the effects of expand and rerank. Only limit is left to name inference, which is acceptable. This fully fills the coverage gap.

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?

Opens with a specific verb and resource: '지식 베이스 하이브리드 검색' (knowledge-base hybrid search), then specifies the mechanism (full-text + vector + IDF + trgm/context, weighted RRF fusion, Slack age decay) and query scope (exact tokens and natural-language concepts). The explicit five-source list (slack, markdown, gitlog, code, note) differentiates this general search tool from the narrow search_code sibling even without naming it.

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?

Provides strong call-time guidance: rerank=true is gated to '정밀도가 중요할 때만' with a cost warning, expand is positioned as a fix for truncated context, and project="*" is prescribed to escape automatic default-project scoping. The 'other-project' mismatch warning tells the agent to read cross-project results cautiously. However, no explicit when-not-to-use or routing to alternatives (search_code, who_knows, get_document) is given.

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