bp_create_graph

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

No annotations are provided, so the description carries the behavioral disclosure burden. It does disclose that this is a mutating operation ('Add', 'create'), requires an existing Blueprint, and returns a StructuredResult with outputs.graph_name. However, it does not explain what happens when a graph with the same name already exists, whether compilation/saving is required, or what failure modes look like.

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 organized with Args, Returns, KB, and Example sections, and the main purpose is front-loaded. But the second sentence largely repeats the first, and the example uses graph_name='EventGraph', which directly contradicts the note saying EventGraph must not be created. The structure is useful but contains redundant and misleading content.

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 simple graph-creation tool, the description covers purpose, parameters, return value, follow-up workflow, and a KB reference. However, it is not fully complete because the blueprint_name format is inconsistent and the only concrete example demonstrates a forbidden EventGraph creation. With no annotations and no schema descriptions, these gaps are not compensated elsewhere.

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 manually documents all three parameters because the schema has 0% description coverage. It gives values and default for graph_type and examples for graph_name and blueprint_name. However, blueprint_name is ambiguous: the Args section says 'Blueprint asset name (e.g. BP_MyActor)' while the example uses a full asset path '/Game/MCP_Test/BP_Example', leaving the agent uncertain which format is actually required.

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: 'Add a new function or macro graph to an existing Blueprint.' It further clarifies scope by saying the graphs are custom function/macro graphs and warns that EventGraph already exists and should not be created. This clearly distinguishes it from node-adding tools like bp_add_node, which the description explicitly points to as the next step.

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 gives a clear use case: 'Use this to create new function graphs that can be called from the EventGraph or other functions,' and it names the follow-up tool bp_add_node. It also includes an explicit when-not: 'EventGraph already exists in every Blueprint — do not create it.' However, it does not explicitly compare against sibling tools such as bp_add_function or add_custom_macro, so it stops short of a full 5.

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