find_blueprint_nodes

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly states the return structure: 'Dict with 'nodes' (full objects) and 'node_guids' (legacy GUID list).' This goes beyond the schema and informs the agent of what to expect. It also clarifies the meaning of each node_type, which affects behavior. However, it does not explicitly state the operation is read-only or mention any side effects, though that is implied. The disclosure of return details and the node_type semantics adds substantial behavior context.

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-structured and every component adds value. It begins with the core purpose, then presents the node_type values in an easy-to-scan bulleted list, followed by an Args section that maps parameters to their meanings, a Returns section, a KB reference, and an example. The information is front-loaded and presented in a logical order. Despite its length, there is no redundant prose.

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 with eight parameters, no annotations, and no schema descriptions, the description is remarkably complete. It covers all parameters, the return format, provides an example, and cites a knowledge base reference. The only gaps are edge cases like error handling, behavior when filters yield no results, or interaction with other tools. Given the complexity, the description is sufficient for an agent to use the tool correctly in most scenarios, but it could still mention potential failure modes or non-obvious interactions.

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 thoroughly documents all eight parameters: blueprint_name, node_type (with enumerated values), graph_name, event_name, function_name, variable_name, input_action_name, and node_name. For each, it explains the purpose and when it applies (e.g., 'when node_type='event''). It also provides defaults for several parameters (e.g., graph_name default 'EventGraph'). This complete parameter documentation leaves no ambiguity about what each argument controls.

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 clear statement of the tool's purpose: 'Find nodes in a Blueprint graph filtered by type and/or name.' It specifies the resource (Blueprint graph nodes) and the filtering capability, distinguishing it from siblings like get_blueprint_nodes (which likely returns all nodes without filtering) and get_node_by_id (which targets a specific node by ID). The description also enumerates the node_type values and their meanings, making the tool's scope unmistakable.

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 implicitly conveys its usage by listing filter parameters and giving an example, but it does not explicitly state when to prefer this tool over alternatives. For instance, it does not mention 'Use this to search nodes by type or name, while get_blueprint_nodes returns all nodes and get_node_by_id retrieves a specific one.' The context of filtering is clear, but there is no explicit 'when-not' or comparison to sibling tools. This leaves the agent to infer the appropriate conditions.

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