ai_anomaly_detection__rolling_deviation_anomalies

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

No annotations provided, so description carries full burden. It states the core behavior (flagging points > threshold sigmas from trailing-window mean) but omits edge cases like incomplete windows, NaN handling, or array start 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?

A single concise sentence with a category prefix. Efficient but would benefit from parameter descriptions.

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?

With 3 parameters, no output schema, and no annotations, the description is incomplete. It explains the algorithm roughly but fails to detail parameters or return value, making it insufficient for reliable agent use.

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 0%. The description vaguely implies 'window' and 'threshold' as parameters via 'trailing-window mean' and 'threshold sigmas', but does not explicitly describe 'values', 'window', or 'threshold'. An agent lacks parameter semantics.

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 clearly specifies the verb 'Flag points' and the resource 'points' from the 'values' array. It distinguishes the tool from siblings (iqr_anomalies, zscore_anomalies) by using a trailing-window mean and sigma threshold.

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 implies usage for detecting outliers based on rolling statistics but does not provide explicit when-to-use or alternatives. Given sibling anomaly tools, this is a gap.

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