rca_pyrca_epsilon_diagnosis

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

The description explains the algorithm (z-score thresholding) and that it flags metrics with |z| > epsilon. Annotations already indicate read-only, idempotent, non-destructive. The description adds context about the distribution comparison without contradicting annotations.

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 well-structured and concise. It opens with a clear purpose, explains the algorithm, gives usage guidance, lists parameters, describes return value, and includes attribution. Every sentence adds value, and there is no redundancy.

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 the tool's complexity (statistical method with specific constraints) and the presence of annotations and input schema, the description covers all essentials: input requirements, algorithm, output format, and usage context. No gaps are evident.

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?

The description explains the key functional parameters (normal_data, anomaly_data, sli_metric, epsilon) with constraints (min 3 values per metric). It adds meaning beyond the schema by describing the role of SLI and the threshold's significance. However, it omits token and client_id, which are present in the schema but not explained.

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 tool's purpose: identifying anomalous metrics contributing to an SLI anomaly using z-score thresholding. It distinguishes from siblings by specifying it's best as a first step before more compute-intensive causal methods, and uses a specific algorithm (epsilon diagnosis).

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 explicitly recommends use as a first step in RCA, implying when to use it. It does not list alternative tools explicitly, but the context of sibling tools and the mention of 'more compute-intensive causal methods' provides clear guidance. No exclusions are given, but it's clear enough.

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