bp_remove_orphaned_nodes

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

With no annotations provided, the description carries the full burden and delivers substantial behavioral detail: only explicitly listed GUIDs are removed, event/entry nodes are always skipped, and the structured result includes removed_nodes, skipped_nodes with reasons, repairs_applied, and a safe_to_continue flag. These disclosures go well beyond a bare mutation statement.

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 well-organized with a core sentence, scoping caveat, Args, Returns, KB reference, and example. Every section adds necessary context without redundant filler, and key constraints are front-loaded before parameter details.

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 covers the operation, preconditions, parameter semantics, return structure, and a concrete example, plus a KB pointer for deeper context. Minor gaps exist around failure modes and whether edits are persisted or compiled, but the detailed output schema and KB reference keep the tool sufficiently self-contained.

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 has 0% description coverage, but the Args section compensates fully: blueprint_path is 'Full asset path or plain name', graph_name is 'Graph to modify', and node_guids is 'List of node GUIDs confirmed orphaned by bp_find_orphaned_nodes or bp_validate_graph.' Each parameter receives meaningful semantics beyond its title.

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 confirmed orphaned nodes from a Blueprint graph.' It further narrows behavior with 'Only nodes whose GUIDs are explicitly listed are removed' and the event/entry-node skip rule, which clearly differentiates it from generic deletion tools like bp_remove_node.

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 tool's usage context is made clear through the node_guids parameter: GUIDs must be 'confirmed orphaned by bp_find_orphaned_nodes or bp_validate_graph.' This implies a find-then-remove workflow, but explicit when-not-to-use guidance or named alternatives (e.g., bp_remove_node for arbitrary deletion) are not stated.

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