rca_analysis_run

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

Annotations indicate write operation (readOnlyHint=false) and not idempotent or destructive. The description adds context: execution triggers analysis, persists results if save=true, and returns JSON with root causes, confidence, explanation. It covers the expected behavior beyond 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 with a concise summary sentence followed by details in docstring format (Args, Returns). It is front-loaded with purpose but could be slightly shorter without losing essential information.

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 and the existence of sibling tools like rca_analysis_run_async, the description lacks mention of synchronous vs asynchronous execution, error handling, or performance implications. The output schema exists but description still covers returns adequately.

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 low (0% per context), but the description compensates by detailing the payload structure per model family, which is critical for correct usage. However, it omits optional parameters like token and client_id, which are present in the schema.

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 executes RCA analysis using a registered model and returns ranked root causes. It explicitly states it is the primary analysis entry point, distinguishing it from sibling tools like rca_analysis_get_result and rca_analysis_batch.

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 provides explicit guidance on what to supply (model_id and family-specific payload dict) and details payload structure per model family. It does not explicitly mention when not to use this tool or list alternative tools for specific scenarios, but labeling it as the primary entry point gives adequate context.

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