batch_retarget_animations

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 discloses that the tool creates new assets (batch-export retargeted copies), that it can skip existing outputs (use_existing_if_found), and that it returns a dict with success/retargeted/skipped/failed counts and raw UE5 log. It also references the KB for deeper context. It doesn't mention side effects like overwriting or asset creation details, but the return structure and skip behavior are disclosed.

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 with a clear summary, workflow context, parameter list, return value, KB reference, and example. It's slightly long but every section earns its place. The parameter list is formatted clearly and the example is useful. The only minor issue is the example uses the same path for retargeter_path and source_animation_paths, which is a bit odd but not confusing.

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 tool has 5 parameters, an output schema, and no annotations. The description covers the workflow context, prerequisites, parameters, return value, and provides an example. It references the KB for deeper detail. It doesn't explicitly state error conditions or what happens if the retargeter doesn't exist, but the return dict with failed count and raw log covers the failure reporting. For a batch operation with this complexity, the description is quite complete.

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: each parameter is listed with a one-line explanation and an example value (retargeter_path, source_animation_paths, output_path, output_suffix, use_existing_if_found). The examples are concrete and match the schema types. The only minor gap is that it doesn't explain the default behavior of use_existing_if_found in detail, but the parameter name and description ('Skip retargeting if the output asset already exists') are self-explanatory.

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's function: 'Retarget a list of animation sequences using an existing IK Retargeter.' It specifies the resource (animation sequences, IK Retargeter), the action (batch retarget/export), and distinguishes it from the single-animation sibling (retarget_single_animation) by explicitly calling out the batch nature. The UE5 editor workflow reference adds concrete context.

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 clear usage context: it is the programmatic equivalent of the UE5 editor 'Retarget Animations → Export Animations' workflow, and it explicitly states the prerequisite ('After setting up the IK Retargeter once (create_ik_retargeter), call this tool'). It doesn't explicitly name alternatives or when-not-to-use, but the sibling list includes retarget_single_animation, and the batch vs single distinction is implied. The KB reference adds further guidance.

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