detect_anomalies

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds interpretive context ('screening signals, not significance tests', 'robust historical scores'), but it does not disclose time-window behavior, sensitivity, or output characteristics beyond what annotations provide.

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 compact sentence with no wasted words, and it front-loads the core concept: unusual spikes/dips in pageviews and revenue. It is appropriately sized, though the parenthetical packing slightly reduces readability.

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 an output schema present and annotations covering safety, the description need not explain return values. Still, for an anomaly detection tool among many analytics siblings, it leaves out the days parameter and does not explain when this is preferable to related investigation tools.

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?

There is one parameter, days, with a default of 30, but schema description coverage is 0% and the description never mentions the time window. For a tool whose only parameter controls the historical lookback, this is a meaningful omission.

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 states a specific phenomenon (unusual spikes/dips) in specific metrics (pageviews and revenue), and clarifies these are screening signals rather than significance tests. It is clear enough, but it does not explicitly name an alternative sibling tool or fully differentiate from investigate_change.

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 parenthetical 'screening signals, not significance tests' provides important usage context and implies when this tool is appropriate. However, it does not state when to use this versus siblings like investigate_change, query_metrics, or compare.

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