get_physics_settings

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

Annotations already declare readOnly/idempotent/non-destructive, but the description goes well beyond them by disclosing three code-level caveats: physics_engine is a hardcoded 'PhysX' literal that misreports UE5's Chaos, the walk only inspects the FIRST primitive component per actor so multi-component actors are undercounted, and generate_hit_events is never populated. That is exactly the kind of hidden-behavior context an agent needs to interpret results.

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?

Front-loads the purpose, then alternatives, then caveats, then a structured returns list, so information ordering is sound. It is dense and long (a scope sentence, three caveats, and a full return-field enumeration), but nearly every clause carries load; the only mild redundancy is restating what the tool counts inside the prose and again in the returns block.

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 zero-param read-only census tool with no output schema, the description supplies everything relevant: what is measured, how counts are derived, the heuristic quality label, and the exact caveats that determine whether the numbers can be trusted.

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?

Zero parameters, so there is nothing for the description to document and the baseline is 4. The description spends its budget on scope and return semantics instead, which is the right allocation.

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?

States a specific verb and resource ('one-shot physics census of the current world') and enumerates exactly what is scanned: UPhysicsSettings substepping/delta-time values, world gravity_z, and a per-actor collision/mobility/mass walk. It explicitly names the siblings it is not (get_collision_info for one component, set_world_gravity / set_physics_gravity to change gravity).

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?

Explicit when-to-use ('broad what-is-the-physics-state-of-this-level sweep instead of hand-writing the actor loop in Python') and when-not, routing the agent to get_collision_info for a single component and to the two gravity setters for mutation. Alternatives and their selecting conditions are all named.

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