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

Even though annotations already declare readOnlyHint, openWorldHint, and idempotentHint, the description adds substantial behavioral context: paper-trading data under a synthetic fixed-book capital model, the requirement for account_type, the behavior of 'live' returning an explicit no-data error, and that the fixed window ensures reproducibility. There is no contradiction with the annotations.

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 long but logically structured with Purpose, Triggers, When to call, Prerequisites, Next steps, Caveats, Args, and Disclaimer. Every section adds distinct value; the length is appropriate for the tool's complexity and the critical caveats about the synthetic capital model.

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 provides a complete operational picture: fixed-window semantics, data source caveats, authentication-like requirement (account_type), reproducibility, and linkage to sibling tools. Given the output schema exists and the description covers all input semantics and edge cases, no critical context is missing.

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 has 0% description coverage, but the Args section fully documents all five parameters: market with aliases and the 'all' 1/3 allocation, account_type as required with paper/live semantics, window_start defaulting to 2026-06-16, window_end defaulting to today KST, and include_daily_curve meaning. This entirely compensates for the schema's lack of descriptions.

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 identifies the tool as providing portfolio-level performance metrics (MDD, Sharpe, Sortino, Calmar, monthly returns, equity curve) over a FIXED window, and explicitly states it is the single canonical computation path for OneQAZ blog and external clients. This distinguishes it from sibling tools like get_trade_history and analyze_trades, which cover underlying trades and breakdowns.

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 triggers ('what's the max drawdown?', 'MDD 얼마야?'), specific when-to-call scenarios (track-record verification, blog figure cross-checks), prerequisites (none), and next steps (get_trade_history, analyze_trades). It also clarifies exclusions, such as 'live' account returning a no-data error until real records exist.

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