rca_graph_merge

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

Beyond the sparse annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint all false), the description reveals key behaviors: duplicate edges keep the higher-weight version, cycle-introducing edges are 'dropped and counted, not silently ignored', source graphs are 'left untouched', and a not_found error is returned for missing or foreign graphs. This is substantial context the annotations do not convey.

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 purpose and behavioral rules, then cleanly organized into Args and Returns sections with every sentence carrying information. It is on the longer side and the Args section partially duplicates the schema, but the added ownership and side-effect notes justify the length.

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 mutation tool with sparse annotations, the description covers purpose, prerequisites, side effects, edge-conflict behavior, parameter semantics, return format, and error conditions. An agent has everything it needs to select and correctly invoke this tool; the optional output schema only reinforces the documented return value.

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?

Even though the context signal reports 0% schema description coverage, the description compensates fully in its Args section: it adds ownership semantics ('both must be yours'), side-effect clarification ('graph_id_a/b are left untouched'), and explains conflict_resolution ('union' default keeps all nodes, 'intersection' keeps only shared nodes). This adds meaning well beyond the schema's terse property descriptions.

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 opens with a specific verb+resource: 'Merge two causal graphs into a unified graph for cross-system RCA', with a concrete example (combining network-layer with application-layer graphs). This clearly distinguishes it from sibling graph tools like rca_graph_create, rca_graph_add_node, or rca_graph_get.

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 usage context via the cross-system RCA example and explicit prerequisites ('Requires the causal_discovery feature (Pro+); both source graphs must belong to you'). It does not explicitly name alternatives or state when-not-to-use scenarios, so it stops short of a 5.

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