Smart-money score calibration

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

Annotations declare readOnlyHint=true and destructiveHint=false, and the description adds key behavioral context: 'out-of-sample evidence,' 'only server-selected cohorts,' and 'caller cannot steer.' This goes beyond annotations by explaining the sampling limitation and the nature of the analysis.

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 a single, well-structured paragraph that front-loads the purpose and outcomes. It uses roughly 60 words to convey purpose, methodology, verdicts, and constraints. While slightly dense, every sentence adds value and there is no redundancy.

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 zero parameters, comprehensive annotations (readOnly, idempotent, non-destructive), and the presence of an output schema (assumed), the description fully covers what the tool does, its limitations (server-selected cohorts), and usage context. It leaves no ambiguity for an AI agent.

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?

With zero parameters and 100% schema coverage, the description does not need to add parameter meanings. The baseline for zero-parameter tools is 4, and the description appropriately focuses on output interpretation.

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 specifies exactly what the tool does: computes Spearman rank correlation between wallet scores and forward PnL, and mean PnL per quartile, returning verdicts like 'insufficient_data' or 'positive'. It includes a directive to read this before treating the score as a forecast, which defines its unique role distinctly from sibling tools like hl_place_order or hl_get_orderbook.

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 states 'Read this before treating the score as a forecast', implying its use for calibration. It also notes that only server-selected cohorts are sampled, so the caller cannot steer results. While it doesn't explicitly list when not to use, the context of being a calibration tool is clear, and no sibling tools serve a similar purpose, making guidance strong.

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