Correlate recovery and training metrics

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

With no annotations, the description carries the behavioral burden. It adds useful transparency with 'Descriptive only' and the optional lag-scan behavior, which signals a read-only analytical purpose. However, it does not explicitly state read-only status, how missing data is handled, what 'compact daily' means in terms of output, or whether date defaults apply.

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 only two sentences, starts with the core action, and every clause adds information: method, metric relationship, lag behavior, descriptive intent, and a prerequisite. There is no filler or repetition 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 8 parameters, no annotations, and no output schema, the description is incomplete for safe invocation. It does not describe the expected output shape, the meaning of 'compact daily correlation,' the behavior of optional date ranges, or the interaction between scanLags and lagDays. An agent would still need to make assumptions about several important execution details.

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%, so the description must compensate. It explains the method choices (Pearson/Spearman), the lag idea, and the athleteId source. But it does not clarify the distinction between lagDays and scanLags, does not mention startDate/endDate at all, and the stated '-7 through +7 day lag scan' does not match the schema's broader -30..30 lagDays range.

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 uses a specific verb and resource: 'Calculate a compact daily Pearson or Spearman correlation between curated wellness and training metrics.' It also names the optional lag-scan behavior and explicitly labels the operation 'Descriptive only,' which helps distinguish it from predictive or modeling siblings like fit_series_model and analyze_series.

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 gives clear context for when to use the tool: when a descriptive correlation between wellness and training metrics is needed. It also gives a prerequisite, 'Requires athleteId from list_athletes.' However, it does not explicitly name alternative tools or state when a different tool should be preferred.

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