Detect Performance Anomalies

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

Annotations already declare readOnlyHint=true, idempotentHint=true, so safe. Description adds valuable behavioral context: rolling baseline, flags specific metrics, and returns structured alerts. No contradictions.

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?

Four sentences, front-loaded with purpose, then lists anomaly types, parameter details, output structure, and usage recommendation. Every sentence adds value; no fluff.

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 no output schema and three params, description fully covers tool behavior, inputs, and output structure. It even suggests daily use. Sibling tools are distinct, and context is sufficient for agent decision.

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?

Description adds meaning for two parameters: sensitivity (z-score threshold) and platform (filter). However, it states lookback_days default as 14, contradicting schema default of 7. Schema coverage is 67% so description partially compensates, but the mismatch reduces reliability.

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?

Clearly states it scans campaigns for statistical anomalies against a rolling baseline, listing specific anomaly types (CPC spikes, CTR drops, etc.). This differentiates it from sibling tools like ab_test_analyze or audience_insights.

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?

Explicitly recommends daily execution ('Run daily to catch issues before they burn budget'), providing a clear when-to-use hint. However, lacks explicit when-not-to-use or comparison with alternatives.

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