rupa_proksi

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description goes beyond by disclosing the critical behavioral trait: the silent failure of Rapier's convexHull above ~8000 points, including a detailed warning with consequences (zero-volume collider, objects falling through world) and mitigation (pre-reduction and exact checks). This is exactly the kind of beyond-annotations context that helps an agent avoid a nasty surprise.

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 front-loaded with the core purpose and integration point, followed by the measurement rationale and a critical warning. It's dense but every sentence adds value; the warning is essential and well-placed. Slightly long for a tool description, but justifiably so.

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?

Given the tool's complexity (3 params, no output schema, annotations for safety), the description covers the key aspects: purpose, integration, measurement methodology, and a critical gotcha. It doesn't describe the return format beyond cost and points, but since there's no output schema, that information is missing. However, the description provides enough for an agent to call it correctly, and the warning is a critical addition.

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 description coverage is 100%, so the schema already documents all three parameters. The description adds context for the 'arah' parameter by explaining how it affects proxy tightness and cost reporting, which is marginally useful, but the basic semantics are already in the schema. No significant compensation needed.

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 states it builds a convex collision proxy from a GLB and measures the cost, with a specific verb and resource. It differentiates from siblings by mentioning it works with rupa_adegan_node's 'cembung' shape, but it doesn't explicitly name an alternative tool for collision generation, though the sibling list includes rupa_tabrakan.

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 implies usage for generating collision proxies, and it provides a specific integration point, but it doesn't explicitly state when to use this over alternatives like rupa_tabrakan. It gives context on measurement methodology (using projectPoint) but no explicit when-not-to-use or alternative selection guidance.

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