rca_graph_discover

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

Annotations lack behavioral hints (readOnlyHint=false etc.), so the description carries most transparency burden. It discloses the algorithm (PC-algorithm with partial correlation), constraints, and return format (JSON with graph_id and edge summary). It does not mention side effects like storage, but the algorithm description is adequate.

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 concise, using a single paragraph with bullet-like args and returns. It efficiently communicates the tool's purpose, inputs, and output without extraneous words. Minor improvement could be better separation of input details, but overall well-structured.

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 (causal discovery), the description covers essential aspects: algorithm, data constraints, and output schema. It does not mention error handling or asynchronous behavior, but these may not be needed. The description is sufficiently complete for an agent to understand when and how to invoke it.

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 input schema already provides descriptions for 'data', 'name', and 'significance' parameters. The description summarizes them but adds minimal new information. With high schema coverage, the baseline is 3, and the description does not significantly enhance semantic understanding.

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: 'Automatically discover a causal skeleton from observational metric data using partial-correlation + Fisher-Z conditional independence tests (PC-algorithm).' It specifies the verb 'discover', resource 'causal skeleton', and methodology, distinguishing it from siblings like rca_graph_create (which likely creates graphs from existing structures).

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 clear context for when to use the tool: for data-driven causal discovery from metrics. It includes constraints (min 30 rows, max 50 variables), guiding appropriate usage. However, it does not explicitly state when not to use or mention alternatives like rca_graph_create, which would improve differentiation.

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