watchlist

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

The description explicitly states the tool can delete items ('삭제') and lists actions 'remove' and 'clear', which are destructive operations. However, the annotations declare 'destructiveHint': false, which directly contradicts the described behavior. No additional behavioral context is provided to offset this contradiction, so the description fails to be transparent and is inconsistent with structured metadata.

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 front-loaded with a clear purpose statement and includes usage examples and integration notes. It is efficient but slightly verbose with the phrase '같은 요청에 사용합니다' and the sharing note. Still, every sentence contributes to understanding, so it is appropriately sized.

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 all core actions, the sharing across Lenses, and provides a concrete integration pattern with other tools. It does not mention edge cases (e.g., behavior when removing a non-existent item) or error handling, but given the tool's simplicity and the existing output schema (not shown), it is reasonably complete for an agent to call it correctly.

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 schema provides only parameter names ('query', 'action') with no descriptions, giving 0% schema coverage. The description fully compensates by explaining 'action' accepts 'list' (default), 'add', 'remove', 'clear', and that 'query' is a stock name or 6-digit code used for add/remove. This adds complete meaning beyond the bare 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 clearly states the tool's purpose: viewing, adding, and removing items from a watchlist ('관심종목 — '내 종목' 목록 보기/추가/삭제'). It uses a specific verb and resource, and distinguishes itself from stock-data retrieval tools by noting it is for list management and shared across three Lenses. Even though it does not name a specific sibling to contrast, the purpose is 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 explicit when-to-use guidance: requests like '내 종목', '관심종목', 'add to watchlist', etc. It also provides a clear alternative: pass the 'codes' from a 'list' result to get_multi_stocks/get_flow_batch/get_indicators_bulk for bulk viewing, and explicitly advises not to look up stocks one by one. This is strong routing and alternative guidance.

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