get_scene_tree

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds real value by describing the shape of the returned text (path, type, world position per prim) and flagging the scale trade-off, though it says nothing about truncation or cost at depth 15.

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 tight sentences, front-loaded with the core purpose and output format, then the sibling pointer. Nothing is repeated or padded.

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 an output schema present, the description needn't explain return values, and annotations cover safety; what it adds — the textual format and the dump_scene alternative — closes most of the gap. The remaining weakness is the ambiguous scale guidance rather than missing core information.

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 coverage is 100% and both parameters are self-documenting, so the schema carries the load. The description only implies that depth/scope matter via the 'large scenes' remark and adds no format or semantics beyond what 'Root' and 'Max Depth' already state; baseline 3 applies.

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 ('Get the USD scene hierarchy') plus the exact output form ('grep-friendly prim-block text'), and names what each entry contains (path, type, world position). This makes it clearly distinguishable from get_prim_properties, get_prim_bounds, and dump_scene without opening a schema.

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 names one alternative (dump_scene) for larger scenes, which is better than nothing. However, the recommendation is counterintuitive — dump_scene 'also includes properties and bounding boxes', i.e. more data for exactly the case where volume is already a problem — and no when-not condition or depth guidance is given.

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