Advance garment physics frames and verify each step's synchronous success. Confirm resulting state before proceeding; reconcile timed-out operations before retrying.
Simulate steps (=frames) and verify synchronous success; does not claim convergence. May change scene or write files. Verify resulting state. A timed-out operation is UNKNOWN: reconcile_operation before any retry.
| Name | Required | Description | Default |
|---|---|---|---|
| steps | No |
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 of behavioral disclosure, and it does so well. It discloses that the tool may change the scene or write files, that it does not imply convergence, and that a timed-out operation should be treated as UNKNOWN. These are exactly the non-obvious behaviors an agent needs to invoke and react to this tool safely.
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?
Four short sentences carry the core action, side-effect warning, required follow-up verification, and timeout handling with no filler. Critical caveats are front-loaded immediately after the core purpose.
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 one-parameter tool with no output schema or annotations, the description covers invocation, side effects, expectations about success, state verification, and timeout recovery. It leaves only minor gaps such as the exact success/error response shape, but the agent has enough to call it and react correctly.
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 coverage is 0% and the description must compensate. It only restates the parameter name in the phrase 'steps (=frames)' and adds the synonym 'frames', but gives no detail about ranges, missing-default behavior, how steps affect execution, or what a reasonable value might be. This is minimal added value beyond the schema's integer/default declaration.
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 states a clear verb ('Simulate'), a specific resource ('steps (=frames)'), and a non-obvious result semantic ('verify synchronous success; does not claim convergence'). This distinguishes it from state-querying siblings like simulation_state and from convergence-oriented operations.
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?
It gives explicit post-call guidance: verify the resulting state and do not blindly retry after a timeout; use reconcile_operation first. It does not enumerate when to use the tool versus related siblings like execute_python or get_simulation_metrics, but the timeout-handling rule is concrete and actionable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.