memory_anomaly

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

With no annotations, the description carries the behavioral burden. It does disclose the core algorithm behavior: z-score is computed and |z| > threshold marks an anomaly. However, it does not state whether the operation is read-only, what data range it uses, or how edge cases are handled.

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 front-loaded sentence with no filler. Every clause contributes information: the target, the method, and the anomaly criterion.

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?

There is no output schema and no annotations, so the description should clarify the return value and usage context. It fails to state what the function returns or how entity is used, leaving an agent without enough information to confidently invoke and consume the result.

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 only 33%; only threshold is documented. The description refers to '某指标' (a metric), giving metric a loose role, but it does not explain the entity parameter at all. Since coverage is low, the description needed to compensate, and it only partially does.

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 operation: detect anomaly points of a metric, with an explicit z-score criterion. It identifies a specific verb and resource, and the content is distinct from sibling tools like memory_trend or memory_causal, though it does not explicitly name or contrast those alternatives.

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 description implies the tool should be used when anomaly detection on a metric is needed, but it gives no explicit guidance about when to prefer it over sibling tools. No alternatives, exclusions, or contextual conditions are mentioned.

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