get_physics_state

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

With no annotations, the description carries the full behavioral burden and does so well. It discloses the mass-only-with-MassAPI caveat, velocity units, and the important timing behavior that velocities are zero until the simulation advances. These are non-obvious traits that an agent must know to interpret results correctly.

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-organized and front-loaded: purpose, return contents, unit caveats, timing caveat, then a bulleted call-when list. Every sentence adds value, and the structure makes the information easy to scan.

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 is complete for a single-parameter diagnostic getter. It covers what is returned, key edge cases, units, timing, and when to invoke the tool. Since an output schema exists, not detailing every return field is acceptable.

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?

The schema has 0% description coverage, but the description compensates with an Args line: 'USD path to the prim to inspect.' This adds domain meaning beyond the raw parameter name and type, though it could have been slightly richer with path format details or an example.

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 opens with a specific verb and resource: 'Diagnostic tool: get physics state for a prim.' It enumerates the returned data (rigid body status, velocities, kinematic flag, collision info), which distinguishes it from broader sibling tools like get_simulation_state and get_scene_info.

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 explicit when-to-use conditions ('Objects fall through the ground', 'Objects don't move when expected', 'Grasping fails'), which is strong practical guidance. It does not name alternative tools or state when not to use it, so it stops short of a 5.

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