compute_lead_lag_relationships

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

With no annotations present, the description carries the full burden and does so thoroughly: exact UTC timestamp matching, no forward-filling, v3 causal RMS scaling, per-lag interval/stability output, no best-lag selection, disabled eligibility/journal promotion due to calibration, and descriptive-only status. This goes well beyond the tool name and schema.

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 dense but every sentence carries distinct information and the primary purpose is front-loaded. There is no repetition of schema fields or filler; the technical constraints are ordered logically from alignment to scaling to output to calibration implications.

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 15-parameter tool with no output schema and no annotations, the description covers a remarkable amount: alignment behavior, defaults, output characteristics, calibration restrictions, and evidence status. It still lacks explicit guidance on the return payload shape beyond interval/stability and on the semantics of some parameters like confidence_level, so it is not fully complete.

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 only 47% and the description compensates for some parameters (symmetric lag range maps to max_lag_bars, prior-20 RMS scaling maps to return_standardization, exact UTC alignment maps to alignment_mode, per-fold stability maps to folds). However, several parameters such as count, confidence_level, folds structure, and the required expected_* fields receive no semantic explanation in either the schema or the description.

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 ('Scan return correlation') on a specific resource ('two explicitly bound layout charts') with a clear investigative goal (whether reference market leads primary). It also distinguishes itself from audit siblings by emphasizing 'Descriptive evidence only, never a trading signal' and by noting no best lag is selected.

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?

It gives clear intended-use context: use this to explore lead-lag correlation via symmetric lags, and explicitly warns it is descriptive evidence, not a trading signal. It does not name alternative tools or give explicit when-not-to-use conditions beyond the descriptive-evidence caveat, so it stops short of a 5.

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