create_ik_rig

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

With no annotations provided, the description carries the behavioral burden. It discloses that creation uses unreal.IKRigController via exec_python, that auto_generate_chains triggers apply_auto_generated_retarget_definition, and that the return value is a dict with success, asset_path, and message. It does not cover overwrite behavior, error conditions, or validation failures, but it provides meaningful behavioral detail beyond the raw operation.

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: an opening summary, a compact workflow list, an Args section, Returns, KB pointer, and an example. It is longer than a minimal description but each section adds useful context, and the most important information is front-loaded. A few sentences, such as the KB reference, are optional but not wasteful.

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?

The description covers the tool's role, workflow position, all parameters, return shape, and an example, which is strong for a 4-parameter asset-creation tool. It lacks explicit information about failure modes, prerequisites like the skeletal mesh existing, and overwrite semantics, but these are relatively minor given the workflow and examples provided.

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?

Despite 0% schema description coverage, the description compensates fully by explaining every parameter: ik_rig_name with an example value, skeletal_mesh_path with a full content path example, path as the destination folder, and auto_generate_chains with behavioral meaning and a recommendation. This goes well beyond the bare schema property names and gives an agent enough semantic context to invoke the tool correctly.

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 identifies the tool's purpose: it creates an IK Rig asset for a Skeletal Mesh and explains that IK Rigs define retarget chains required by the IK Retargeter. It distinguishes this tool from siblings like create_ik_retargeter and add_ik_rig_retarget_chain by focusing on asset creation rather than retargeting or chain editing.

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 provides a numbered typical workflow showing when to call this tool for source and target skeletons, followed by create_ik_retargeter and batch_retarget_animations. It also gives conditional guidance on auto_generate_chains for humanoid skeletons versus custom setup. It does not explicitly state when not to use the tool, but the workflow strongly implies the correct context.

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