rca_graph_score

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, covering the safety profile. The description adds meaningful behavioral context by listing the structural metrics returned, including that the two scores are in [0,1], and clarifying this operation does not perform root-cause analysis. No contradiction with 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 front-loaded with the core purpose, then provides usage context, args, and return values. Every sentence or block is informative and there is no filler or 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?

For a simple scoring tool, the description is complete: it explains what it does, when to use it, what it returns, and how the scores behave. The annotations and input schema cover safety and parameters, while the return-values listing fills any gap for agents that cannot infer output shape.

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 schema already provides descriptions for token, graph_id, and client_id, so the baseline is adequate. The description only repeats 'graph_id -- the graph to score' and does not mention token or client_id, but the schema fills that gap. It adds little beyond 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 states a specific action and resource: 'Compute structural quality scores for a causal graph'. It also explicitly scopes the tool as a structural sanity check, not root-cause analysis, and mentions checking for valid DAG and connectivity, which distinguishes it from related tools like rca_analysis_run and rca_graph_score_paths.

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 gives explicit when-to-use guidance: after building or editing a graph by hand, or after rca_graph_discover, before running rca_analysis_run. It also clearly states a when-not-to-use condition by saying this is 'not a root-cause analysis', which prevents misuse.

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