Runs ordered Unreal steps in a single call and reports partial results, so a failed step keeps prior successes and an unresponsive editor aborts remaining steps.
Run ordered steps in one call with PARTIAL reporting: a step that fails does not erase the ones that already ran, and an editor that stops answering aborts the rest instead of dropping them silently.
| Name | Required | Description | Default |
|---|---|---|---|
| steps | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it does disclose real behavior: partial results survive a failing step and an unresponsive editor aborts rather than silently dropping remaining steps. However, it never says whether steps after a failure still execute, how errors surface, or what the per-step timeout means, which are exactly the ambiguities that matter for a batch executor.
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?
One front-loaded sentence that leads with the action and then the reporting behavior. No filler, though the partial-reporting clause is packed tightly enough that its meaning is slightly murky.
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?
No output schema and no annotations for a tool whose whole value is reporting per-step outcomes, yet the description never says what comes back on partial success. Combined with zero parameter documentation and a 64-step cap disclosed only in the schema, an agent cannot reliably call or interpret this tool from the description alone.
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% and the single parameter is a nested array of step objects (domain, action, params, timeout, maxItems 64). The description adds nothing about these: no ordering semantics, no explanation of how per-step params pass through, no timeout units or per-step vs global scope.
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?
"Run ordered steps in one call" states a batching verb and hints at multi-step orchestration, but never says what a step is or that it dispatches into the domain siblings (world/blueprint/material/...). The agent must read the nested enum to infer that this is a fan-out across domains rather than a distinct capability.
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?
There is no guidance on when to batch via ue_pipeline versus calling ue_world, ue_blueprint, ue_material, ue_media or ue_vision directly. Ordering is mentioned but not as a selection criterion, so the agent gets an implied usage rather than explicit routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.