scene_bounds

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds that the payload is axis-aligned min/max plus a unit scale, but since an output schema exists this return detail is partly redundant and no extra behavior (units assumed, empty-scene behavior) is disclosed.

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?

A single tight sentence with the resource front-loaded and the return format appended; nothing wasted. It is, however, terse to the point of omitting any routing context.

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?

With no parameters, a full output schema, and complete annotations, most of the burden is already carried by structured data, so the description is minimally sufficient. It still leaves the agent guessing about scene-state prerequisites and how it differs from other scene-wide queries in a very large sibling set.

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 tool takes zero parameters, so there is nothing to document and the baseline 4 applies. The description adds no misleading parameter-like language.

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 resource (scene bounds) and the exact result shape ([min_xyz, max_xyz] plus unit scale), so an agent knows precisely what comes back. It doesn't distinguish itself from nearby siblings like scene_info or camera_frame, which keeps it short of a 5.

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?

There is no indication of when to call this versus scene_info, scene_list_objects, or selection_get, and no preconditions such as requiring a loaded scene. The agent must infer usage purely from the name and result shape.

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