Find statistical wellness anomalies

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

With no annotations, the description carries most of the behavioral disclosure burden. It usefully states that the tool 'does not diagnose or prescribe' and that it groups anomalous dates across signals. It does not explain return format, default date ranges, or what happens when no anomalies are found, so transparency is partial.

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 two sentences with no filler. The primary purpose and behavior are front-loaded, followed by an essential caveat and prerequisite. Every sentence contributes meaningful guidance.

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?

The description is incomplete relative to the tool's complexity: five undocumented parameters, no output schema, and no annotations. It omits date range semantics, default metric or threshold behavior, and return value shape. The non-diagnostic caveat and grouping detail are helpful but not enough for reliable invocation in ambiguous cases.

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 schema provides no parameter descriptions, so the description must compensate for five parameters. It adds meaning by explaining the z-score approach, implying metric selection through 'multiple signals,' and sourcing athleteId 'from list_athletes.' It does not explain startDate, endDate, zThreshold defaults, or the specific metrics enum, leaving gaps.

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 action, 'Find daily recovery and wellness outliers by z-score,' and a clear output behavior, 'group dates with anomalies across multiple signals.' It distinguishes the tool from generic data or activity tools, though it does not explicitly contrast it with sibling wellness tools like wellness_baselines or wellness_correlate.

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 provides a useful prerequisite, 'Requires athleteId from list_athletes,' which tells the agent where to source a required value. However, it does not state when to prefer this tool over alternative wellness or anomaly-related siblings, nor does it give exclusions or explicit when-not-to-use guidance.

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