create_action_graph

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

With no annotations, the description carries the behavioral disclosure burden, and it does so well: it reveals that the tool uses og.Controller.edit(), auto-creates and wires OnPlaybackTick → ScriptNode for shortcuts, sets usePath/scriptPath vs inline, and that nodes/connections are ignored when script_file is set. The evaluator explanation is especially valuable, describing how 'push' keeps an OnPlaybackTick-driven ScriptNode running even when simulation is stopped. It does not mention side effects like idempotency or failure modes, but the disclosed behavior is substantial.

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 long but structured with clear sections, parameter explanations, and examples, which suits the tool's complexity. It is front-loaded with the core purpose and then elaborates on parameters. There is minor redundancy around the 'better reload story' phrasing repeated for both script_file and inline_script, but it does not significantly harm readability.

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?

Given the tool's complexity and the absence of annotations, the description is largely complete: it covers creation mechanics, all meaningful parameter semantics, evaluator behavior, and provides usable examples. The main gaps are the undocumented command_id/idempotency_key parameters and the lack of explicit guidance about when to choose this tool over edit_action_graph or connect_action_graph.

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 does for most parameters: graph_path, nodes, connections, values, evaluator, script_file, and inline_script are all explained with concrete shapes and examples. However, command_id and idempotency_key are not described at all, leaving two of nine parameters without semantic explanation.

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 verb and resource: 'Create and wire an OmniGraph Action Graph' and explains it builds a complete graph with nodes, connections, and attribute values. It is distinguishable from siblings like delete_action_graph, get_action_graph, and edit_action_graph by framing itself as the programmatic equivalent of creating a graph in the visual editor.

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 explicit usage guidance for choosing between script_file and inline_script: script_file is recommended for iteration, inline_script for small static graphs. It also explains when nodes/connections are ignored (when script_file is set). However, it does not explicitly contrast create_action_graph with edit_action_graph or connect_action_graph, so the broader alternative-selection guidance is partially implicit.

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