ml_detect_anomalies

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

Annotations already declare readOnlyHint=true and openWorldHint=true, and the description adds that it performs anomaly detection, which is consistent. However, the description does not elaborate on behavioral traits beyond the annotations, such as output format or side effects.

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, dense sentence with no redundant words. It is front-loaded with the core purpose and is appropriately sized for the tool's simplicity.

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 the lack of an output schema, the description does not explain what the tool returns (e.g., anomalies with scores, timestamps). Additionally, there is no guidance on parameter interactions or typical usage context, leaving the agent potentially underinformed.

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 input schema has 100% coverage with descriptions, so the schema already explains all parameters (days, field, table, threshold). The description adds no additional meaning beyond the schema.

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 states the action ('Run anomaly detection') and the target ('operational metrics' like alert volume, incident trends). This differentiates it from sibling tools such as ml_forecast_incidents or ml_predict_change_risk.

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 anomalies in operational metrics but provides no explicit guidance on when to use versus alternatives, nor when not to use it. It lacks contextual cues for agent decision-making.

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