rca_graph_merge

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

With no annotations aside from non-destructive hints, the description carries full burden. It discloses duplicate edge handling (keep higher weight), cycle handling (dropped and counted), and return format (JSON with counts). This is comprehensive but could further clarify whether original graphs are modified or if the operation is safe to repeat.

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 extremely concise and well-structured: a clear opening sentence defining the purpose, followed by bullet-point style Args and Returns sections. Every sentence adds value, and the most important information is front-loaded.

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 moderate complexity and the presence of an output schema (so return details are not required), the description covers merge behavior and conflict resolution. However, it lacks mention of required authentication (token), side effects on original graphs, and error conditions. These gaps reduce completeness.

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 lists four key parameters (graph_id_a, graph_id_b, merged_name, conflict_resolution) and explains conflict_resolution values. However, it omits the required 'token' and optional 'client_id' parameters present in the schema. With 0% top-level schema description coverage, the description partially compensates but misses critical auth details.

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 verb 'Merge' and the resource 'causal graphs', with a concrete example (combining network-layer and application-layer graphs). It distinguishes this tool from siblings like rca_graph_create or rca_graph_add_edge by specifying its cross-system graph merging role.

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 usage for merging two distinct causal graphs (e.g., from different layers), but does not explicitly state when not to use this tool or provide alternatives. No mention of prerequisites or conditions where other tools like rca_graph_create would be more appropriate.

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