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

The description discloses computation-only behavior, consistent with readOnlyHint=true. It warns about liquidation inside stop and mentions caps by orderbook liquidity, adding behavioral context beyond 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?

Three efficient sentences: first lists outputs, second warns about liquidation, third advises on parameter grounding. No redundant words, front-loaded with key action.

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?

With 8 parameters and no output schema, the description adequately outlines the major outputs and purpose. It could include return format or more details on liquidity capping, but it's sufficient for an agent to understand tool scope.

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 coverage is 100%, and the description adds usage context (e.g., grounding win_rate, capping by liquidity). While individual parameter details are in schema, the description gives semantic meaning to the overall computation and parameter interplay.

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: turning a signal and bankroll into a concrete position, listing specific outputs like fractional-Kelly size, stop, liquidation price. It distinguishes from other get_* tools which focus on data retrieval, not position sizing.

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 advises grounding win_rate_pct with get_signal_performance or get_signal_backtest first, providing explicit prerequisite guidance. However, it does not explicitly state when not to use or give alternatives beyond that.

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