remove_pcg_node

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

Discloses internals beyond the annotations: UPCGGraph::RemoveNode auto-breaks edges and notifies neighbours, the graph is re-saved, and endpoint nodes are rejected with a non-silent error. These are exactly the mutation consequences an agent needs, on top of the destructiveHint/idempotentHint flags.

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 action is front-loaded and the sentences each carry weight (semantics, side effects, edge case, idempotency, return shape). The trailing Returns block is dense but useful given no output schema; the C++ class reference is slightly over-detailed but harmless.

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 2-param mutation with annotations and no output schema, the description covers side effects, saved state, endpoint rejection, idempotency, and even enumerates the return fields. An agent has everything needed to call it correctly.

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?

Schema description coverage is 100%, so both parameters are already documented in the schema (including the node_name source and endpoint rejection). The description adds only the 'by name' phrasing, so baseline 3 applies.

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?

States a specific verb (Removes), resource (a user-added node from a PCG graph), and scoping constraint (by name). The 'user-added' qualifier and endpoint restriction distinguish it from the broader PCG toolset without needing the schema.

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?

Gives clear conditions: only user-added nodes, endpoint nodes rejected, and idempotent behavior for missing nodes. However, it never routes the agent to an alternative (e.g., disconnect_pcg_nodes when edges should be preserved), so it stops short of explicit when-to-use-vs-sibling guidance.

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