create_usd_stage

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

Annotations already declare the non-readonly, non-destructive safety profile, but the description adds real behavioral context beyond them: the stage is registered in GStageNameCache under stage_name, memory-only stages cannot be persisted, and cleanup requires close_usd_stage. It does not mention permission or error prerequisites, keeping it from a 5.

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?

Front-loads the core action, then the mode distinction, then the registry side effect, then the return shape. Every sentence is information-bearing. It is dense, and the inline return-field listing makes it longer than strictly necessary, but nothing is wasted.

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 output schema, the description compensates by spelling out the returned object fields (stage_name, file_path, memory, identifier, real_path, dirty, is_valid, errors). Combined with the lifecycle and cleanup notes, an agent has everything needed to call and follow up on this tool correctly.

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 params are documented, but the description still adds semantic consequence: file_path creates a root layer file at that exact path, and omitting it yields an anonymous 'anon:0x...' identifier. This goes beyond the schema's syntax description by explaining what the value does downstream.

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+resource (create a USD stage) and immediately distinguishes the two modes (on-disk vs in-memory) that the single tool supports. An agent can tell it apart from open_usd_stage and create_usd_stage_actor without opening any 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?

Clearly explains the condition that selects each mode: file_path present -> on-disk root layer; omitted/empty -> memory-only, with the caveat that this is the only way to author a non-persisted stage. It also points to close_usd_stage as the cleanup path. It stops short of explicitly contrasting with open_usd_stage for existing stages, so not a full 5.

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