广告异常检测

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds meaningful behavioral scope by identifying the specific anomaly categories being tested, which is useful context beyond the annotations. No contradiction exists.

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 filler or repetition. It front-loads the core action and immediately lists the anomaly types, making efficient use of the space.

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?

For a read-only anomaly-detection tool with annotations covering safety, the description is mostly adequate. But with no output schema, it does not state what the tool returns (e.g., a list of flagged anomalies or counts), and it omits the role of report_id. These are notable but not severe gaps.

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 the description must compensate. It does map 'ACOS threshold' and 'CTR threshold' to max_acos and min_ctr, adding meaning beyond the bare schema. However, the required report_id parameter is not explained, and default threshold behavior is left entirely to schema defaults.

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 verb ('检查' / check) and the specific resource (ad anomalies), and enumerates concrete anomaly types: burning money with no revenue, high ACOS, low CTR, and clicks without orders. This differentiates it from sibling tools like inventory_risk_detect or product_metrics_get.

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 context is implied: use this when you need to detect ad anomalies against ACOS and CTR thresholds. However, there is no explicit guidance about when not to use it, nor does it contrast with alternatives such as product_metrics_get or inventory_risk_detect.

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