run_lead_lag_falsification_audit

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

With no annotations, the description compensates by disclosing the null mechanism (circular-shift empirical null after v3 default scaling), reproducibility through a configuration hash, and non-effects (does not read/change TradingView, does not establish profitability). It stops short of failure modes or resource costs, but covers the most decision-relevant behavior.

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 sentences, front-loaded with purpose, and each sentence adds a distinct behavioral fact: null method, scaling, reproducibility, and side-effect absence. It is not bloated, though the third sentence packs several technical clauses that could be split for readability.

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?

High parameter count, near-zero schema description coverage, no annotations, and no output schema place a heavy burden on the description, which it only partially meets. It provides methodology and side-effect context, but not enough for correct invocation of required parameters or interpretation of the returned result.

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 only 8%, so the description must carry parameter semantics; it explains null variants and default scaling but never maps concepts to specific parameters like model, folds, replications, or nominal_alpha. Only return_standardization has any schema-level description, leaving required inputs largely undocumented.

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 verb ('Calibrate') and a specific resource ('frozen lead-lag candidate rule') against paired nulls, making the tool's core function clear. It is distinguishable from sibling falsification audits because it targets lead-lag rules specifically, though terms like 'frozen' and 'candidate rule' rely on domain context.

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?

No explicit when-to-use or when-not-to-use guidance is provided, and no alternative tools are named even though sibling falsification audits exist. The factor/independent variant explanation hints at use cases but does not state prerequisites or how to choose among the 13 parameters.

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