add_hit_event

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

No annotations are provided, so the description carries the full burden. It states the node fires when actor is hit by collision, which is useful, but it doesn't disclose side effects: whether it modifies the blueprint graph, whether it requires compilation, whether it can create duplicate nodes, or what happens if the blueprint doesn't exist. The example shows a path format but doesn't explain error behavior or node placement details.

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 compact: a one-line summary, an Args section, a KB reference, and an example. It's front-loaded with the core purpose. The KB reference and example are useful, though the Args section largely repeats parameter names. No wasted words, but the structure could be tighter by integrating the example into the main description.

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 tool that modifies a blueprint graph, the description lacks critical context: no mention of whether the blueprint must be loaded, whether the node is placed in the event graph, how node_position is interpreted, or what the output schema contains (though output schema exists, the description doesn't reference it). The KB reference helps but is not sufficient. The example is good but doesn't cover error cases or prerequisites.

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 0%, so the description must compensate. It lists blueprint_name and node_position with brief explanations ('Blueprint name', 'Optional graph position'), but these are minimal and don't add much beyond the parameter names. The example shows blueprint_name format ('/Game/MCP_Test/BP_Example') which is helpful, but node_position format (array of numbers) is not explained—what coordinates, what order, what units? The description doesn't fully compensate for the 0% schema coverage.

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 tool adds an OnActorHit event node to a blueprint and explains what the event fires on (actor hit by collision). It distinguishes itself from the sibling add_overlap_event by naming the specific event type. However, it doesn't explicitly contrast with add_overlap_event or other event-adding tools, so it's clear but not fully differentiated.

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 context: it's for adding an OnActorHit event node to a blueprint, and the example shows a typical call. It doesn't explicitly state when to use this over alternatives like add_overlap_event or add_on_see_pawn_event, nor does it mention prerequisites (e.g., blueprint must exist, must be in graph editing mode). The KB reference provides some guidance but is not explicit about selection criteria.

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