run_event_study_falsification_audit

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

With no annotations provided, the description carries the full burden and does so well. It explicitly describes separate null-model runs, the candidate criterion, the returned metrics, and important non-behaviors such as not touching TradingView, not journaling, not ranking variants, and not establishing profitability.

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?

Four dense, information-packed sentences with the purpose front-loaded. Every sentence contributes either scope, output, acceptance criteria, or side-effect boundaries; there is no 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?

For a complex tool with no annotations and no output schema, the description covers core outputs, the candidate rule, and behavioral boundaries well. However, it omits one supported study type and does not explain how failures are represented or when to choose this over sibling falsification/power audit tools.

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 description adds meaning for models, synthetic folds, and the seed-range output, but leaves first_seed and volatility behavior implicit. It also underrepresents the study parameter by naming only FVG-retest and session-auction while the schema includes a third variant.

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?

States a specific verb 'Calibrate' and a specific resource—one frozen event-study decision rule against synthetic OHLC—and enumerates the key outputs. It also distinguishes itself from ranking/profitability tools, though it omits the event_aftershock_retest variant that appears in the schema.

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 intended usage is implied: use when a single frozen event-study rule needs falsification against synthetic data with separate null-model runs. Negative boundaries are given, but no explicit alternative tool or when-not condition is named, so the agent must infer routing from context.

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