Insights anomalies

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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so the safety profile is covered. The description adds real value by disclosing the statistical baseline (each campaign's own history) and method (robust z), but says nothing about how the threshold governs flagging, minimum history requirements, or sparsity handling.

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 sentence, front-loaded with the resource (“Campaign anomalies”) followed by the comparison basis and metrics. Every clause carries information; nothing is repeated from the title or schema.

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 available and annotations covering safety, the description only needs to convey purpose and method, which it does compactly. The remaining gap is scope — which platforms/accounts the “campaigns” span relative to the cross-network siblings — but that is a minor omission for a read-only diagnostic tool.

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 description coverage is 0%, so all meaning must come from the description. It implicitly defines the history window behind `days` and ties `threshold` to a robust-z cutoff, but never states units, boundary behavior, or anything about `customer_id`, leaving that required parameter to inference.

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?

Specific verb-and-resource framing: it detects campaign anomalies by comparing the latest day against each campaign's own history, with the metrics named (cost, conversions, clicks) and the method given (robust z). An agent knows precisely what analytical output to expect, though it does not explicitly distinguish itself from neighbors like insights.pacing or ads.fields.deltas.

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?

Usage is implied rather than stated: “latest day vs each campaign's own history” suggests a daily anomaly-scanning use case. There is no explicit when-to-use versus when-not, and no named alternative among the many insights.* and ads.report.* siblings that could surface similar deltas.

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