rupa_tabrakan

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

Annotations already signal destructiveHint=true; the description does not contradict that. It adds useful constraints such as dynamic trimesh not being supported by most engines and clarifies the behavior of `tembus` and `longgar`, but it does not say what is actually mutated or what the invocation result is.

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 core purpose is front-loaded and the rest of the description explains only relevant jargon and constraints. The technical details are compact and not redundant, even though the phrasing is dense and assumes some collision-proxy familiarity.

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 four-parameter mutation tool with no output schema, the description does not fully clarify what object or current scene receives the proxy, nor what a successful call returns. It provides strong domain detail but leaves the invocation contract partially implicit.

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 description adds meaningful semantics around the `bentuk` parameter and the meaning of proxy surface gaps, which the schema does not fully provide. With only 50% schema description coverage, it still leaves `objek` semantically implicit and does not tie every parameter to its intended function.

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 establishes that the tool deals with collision proxies and explains the two error directions, so it is not a tautology. However, it never states an action verb such as 'create' or 'update', and it does not differentiate the tool from siblings like rupa_proksi.

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 concrete when-to-use guidance for shape selection: `cembung` is the workhorse for web physics engines like Rapier, and `mesh_sederhana` should be used only for static objects. But it gives no context on when to use this tool as a whole versus related tools, so the guidance is incomplete.

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