run_feature_outcome_falsification_audit

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

With no annotations, the description carries the full behavioral disclosure burden, and it does so well by stating that the tool uses deterministic synthetic null OHLC, applies a specific statistical rule set, and has no TradingView or journal side effects. It does not mention computational cost or output behavior, but the side-effect profile and methodology are clearly disclosed.

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 three tight sentences: purpose, statistical criterion, and exclusions. Information is front-loaded and every sentence earns its place, with no redundant filler or restatement of the tool name.

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 the high complexity (24 parameters, 6 required, no annotations, no output schema), the description is too sparse to fully support correct invocation. It explains the high-level methodology but omits what the tool returns, how results are reported, and how to choose the six required parameters, making it incomplete for an agent facing novel inputs.

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%, and the tool has 24 parameters, yet the description provides almost no parameter-level guidance. Terms like 'horizon-one' and '1,000-replication' hint at horizons and replications, but required parameters such as minimum_observations, minimum_effect_bps, and configuration_trials are not explained, leaving an agent without enough information to set values correctly.

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 states a specific action ('Calibrate the frozen feature-outcome candidate gate'), a precise target ('deterministic synthetic null OHLC'), and enumerates what the tool does not do, which distinguishes it from sibling tools such as event-study or ranking-related audits. This is far from a tautology and gives an agent a clear operational picture.

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 conveys clear context: use this tool to calibrate a feature-outcome candidate gate against synthetic null data and apply specified falsification rules. It also provides explicit exclusions (does not read/change TradingView, journal, rank, or establish profitability), which helps an agent avoid misuse, though it does not name alternative sibling tools or state an explicit when-to-use formula.

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