get_trade_log

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

No annotations are provided, so the description carries the full burden. It discloses that the data source is local storage ('로컬에 저장된') and the content type (AI trade rationale/indicators), but it does not explicitly state that the operation is read-only, how results are ordered, or whether the log is strictly append-only. The 'get' prefix implies read-only, but this is not fully explicit.

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 two concise sentences. The first sentence front-loads the core purpose (query locally stored AI trade history), and the second adds useful context about its strategic use. There is no redundancy or 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 tool has 5 optional parameters, no annotations, and no output schema. The description explains the purpose and general content (trade rationale/indicator state), but it does not describe the return shape, default sort order, or clarify how this differs from get_trades. Given the lack of output schema and the close sibling, the description is adequate but leaves gaps about expected return data and edge cases.

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 input schema provides 100% parameter description coverage, including filters for side, limit, symbol, and date range. The description adds only the conceptual context of '과거' (past) and '근거·지표 상태' (rationale/indicator status), which does not materially extend the parameter meanings already present in the schema. 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?

The description uses a specific verb ('조회합니다' - retrieves) and a clear resource ('AI 매매 이력' - AI trading history). It distinguishes itself from sibling tools like get_trades and get_orders by emphasizing '로컬에 저장된' (stored locally) and '근거·지표 상태' (rationale/indicator status), indicating this is a log of AI decision context rather than raw trade executions.

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 second sentence explicitly explains when to use the tool: to understand past trading rationale and indicator states for current strategy decisions. This provides clear usage context, though it does not explicitly mention when not to use it or point to alternatives like get_trades for broker-executed trade history.

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