rca_graph_remove_node

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

Even though destructiveHint=true already flags mutation, the description adds valuable context: the operation is destructive and irreversible through this tool, and it explains the only undo paths. It also discloses error behavior (not_found/value error) and warns that the node name is case-sensitive, going well beyond the annotation.

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 logically covers usage disambiguation, undo/recovery, parameter semantics, and return behavior. Each section earns its place and the text remains structured and readable despite covering a destructive operation with several caveats.

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?

The description is complete for this complexity level: it states the operation, destruction semantics, undo strategy, when-to-use guidance, parameter hints, and return format. It even handles the edge case of an unknown node name, leaving no critical ambiguity for an agent.

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 adds meaning to key parameters by explaining graph_id as 'the graph to modify' and name as the exact, case-sensitive node name, plus advising rca_graph_get to confirm the name. While the top-level schema coverage is low, the nested schema already describes token/client_id, so the description's partial parameter guidance is sufficient and actionable.

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 and resource: 'Remove a node and all its incident edges from a causal graph.' This clearly distinguishes it from rca_graph_remove_edge, rca_graph_add_node, and rca_graph_delete, so an agent can immediately understand what operation this tool performs.

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 explicitly states when to use the tool ('correct a mistaken node') and when not to use it ('not to prune weak paths'), pointing to alternatives like adjusting edge weights or using rca_graph_score_paths first. It also gives recovery guidance via rca_graph_add_node/rca_graph_add_edge or rca_graph_restore_version.

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