compare_strategies

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

With no annotations, the description carries the burden of behavioral disclosure. It does disclose that the tool runs every strategy and ranks results, and it adds a caveat about statistical reliability. However, it does not explicitly state side effects, computational cost, data requirements, or that it is a non-trading simulation. The statistical caution is useful but not a substitute for operational transparency.

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 well-structured: a one-line purpose, a concise argument list that maps to the schema, and a two-sentence caution. Every line earns its place; no fluff. The most important usage warning is placed at the end for emphasis without bloating the text.

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?

Given 7 parameters, no annotations, and an output schema present, the description provides sufficient context: purpose, parameters, and a statistical validity caveat that affects decision-making. It could mention that it is a historical backtest or that it assumes availability of the listed market/interval, but the sibling context and note about walk_forward_backtest fill that gap. The output schema handles return value details.

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%, but the description compensates by defining all seven parameters in the Args section, including enumerated values for market ('crypto', 'stock', 'idx') and rank_by ('sharpe', 'total_return_pct', 'calmar', 'profit_factor'). It provides meaningful semantics like 'Candles to test over' and 'Fee in basis points per position change.' Minor gaps remain: no ranges, units for interval, or constraints, but coverage is solid.

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 action: 'Run every strategy on one instrument and rank them,' which clearly states what the tool does and its output. It distinguishes itself from siblings like backtest_strategy and walk_forward_backtest by emphasizing the comparative, one-symbol ranking nature. The resource and result are 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 explicitly warns that a leaderboard over one window is a weak signal and instructs to confirm findings with walk_forward_backtest. This gives clear when-to-use and when-not-to-use guidance, and names the appropriate alternative. It implicitly contrasts with single-strategy backtests, aiding tool selection.

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