pick_3d_point

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description adds independent value with the mesh/splat null-index caveat and the explicit assurance about not moving the camera. It also discloses the return payload, which sets accurate expectations.

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?

Two compact sentences with no filler. The core action and the most critical caveat are front-loaded, and every clause contributes useful information.

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 read-only pick tool with an output schema, a defaulted enum, and simple required params, the description covers the essential usage conditions and the important null-indices warning. The only minor gap is not explicitly explaining the 'detail' parameter, but the enum and the existence of an output schema mitigate the risk.

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 0%, so the description must compensate. It does for the 'screen' parameter by explaining 'normalized canvas XY,' which matches the 0..1 range constraints, but it does not explain 'scene_id' or clarify how 'detail' affects the output. The return-payload sentence hints at output content but does not connect it to the parameter.

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 ('Pick'), resource ('normalized canvas XY'), and the key behavior ('without moving the camera'), which distinguishes it from camera navigation and capture siblings. It also names the return fields, so an agent knows exactly what the tool does.

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 'without moving the camera' phrasing gives clear context that this is a read-only picking operation rather than a navigation/capture tool. It does not explicitly name an alternative or provide when-not-to-use guidance, but the context is sufficient for selection among the sibling tools.

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