get_simulation_metrics

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

With no annotations, the description carries full behavioral weight. It warns that the operation may change the scene or write files, says to verify resulting state, and clarifies that a timed-out operation is UNKNOWN and must be reconciled before retrying. This is unusually transparent about side effects and failure semantics.

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?

Every sentence earns its place: purpose, side effects, comparison precondition, and timeout handling. The description is dense but front-loaded with the core function and ends with the most critical failure behavior. No filler or repetition.

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 side-effecting 'get' tool with one param and no output schema, this is fully complete. It covers what the operation returns, when comparison is valid, side effects, verification expectations, and how to handle timeouts. An agent has everything needed to call and interpret this tool 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 there is one optional parameter. The description compensates by explaining how previous_snapshot_id should be used and what preconditions apply (topology match, no persistent IDs). It doesn't fully define the ID format or how it is obtained, but it gives enough operational meaning for an agent to use it safely.

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 as an on-demand operation that gets garment OBJ positions and index-based displacement, and explicitly states it never judges convergence. It also mentions writing an OBJ measurement in user cache, which distinguishes it from simulation_state and export_obj.

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?

Provides concrete usage conditions: compare to previous_snapshot_id only if topology matches, no persistent vertex IDs or collision/convergence guarantee, and calls out reconcile_operation as the required follow-up after a timeout. This gives an agent explicit when-to-use and what-not-to-assume guidance.

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