Detect Spend & CPA Anomalies (Guardrail)

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

Since no annotations are provided, the description carries the full behavioral burden. 'Scans' and 'recommends' convey that the tool analyzes and advises rather than mutating campaigns, and the list of detected conditions tells the agent what signals drive the tool. It stops short of explicitly declaring read-only status or describing response shape, but the non-mutating intent is clear.

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?

Two sentences with no filler: the first front-loads what is scanned and the anomaly categories, the second states the recommendation-oriented output. The detail in the anomaly list earns its place by clarifying detection semantics.

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?

All four parameters are optional and self-documenting, so the description covers the invocation trigger without repeating schema details. Since there is no output schema, the note that it recommends remediation actions gives a reasonable expectation of the return value, though a precise output structure is not specified. This is adequate but not exhaustive.

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 100%, so parameters are already individually documented with defaults and ranges. The description adds no new parameter-level information but reinforces semantic context through the anomaly types it mentions. The baseline of 3 is appropriate because the schema does the heavy lifting.

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 names the resource (delivery and conversion metrics across campaigns) and the specific verbs (scans, detects, recommends), then enumerates concrete anomaly types: runaway spend, zero-conversion budget drain, low-CTR creative burnout, and abnormal CPA spikes. This makes it clearly distinct from generic metrics or analysis siblings like get_delivery_insights and analyze_campaign_performance.

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 text establishes a clear guardrail use case: use this when you need to identify spend/CPA anomalies and get recommended remediation actions, not merely raw metrics. It does not explicitly name alternatives or state when not to use it, but the intended context is clear enough to route an agent correctly.

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