create_usd_attribute

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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false). The description adds real behavioral context beyond that: the mutation is in-memory only until save_usd_stage, and re-invoking returns the existing attribute with created=false rather than duplicating. This persistence and get-or-create detail is valuable and not encoded in the annotations.

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 purpose is front-loaded in the first sentence, followed by persistence and follow-up guidance. The return fields are stated twice (inline and in a Returns block), which is mildly redundant, but the overall length is appropriate for the tool's complexity.

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 correctly carries the return contract (prim_path, name, type_name, cpp_type, created). Combined with the open-stage precondition, in-memory edit model, save step, and the pointer to set_usd_attribute_value, an agent has everything needed to invoke and chain this tool.

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 all four parameters (attr_name, prim_path, type_name, stage_name) are already documented with examples in the schema. The description references the USD type but adds no syntax or format detail beyond what the schema provides, so the 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 (create an attribute of a given USD type on a prim of an open stage) and clarifies the get-or-create semantics (returns existing with created=false). It also distinguishes itself from the sibling set_usd_attribute_value by naming that tool as the way to author the value.

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?

Gives clear workflow context: the stage must already be open, edits are in-memory, and save_usd_stage persists them; set_usd_attribute_value is named for the follow-up step. It lacks an explicit when-not-to-use statement, but the surrounding guidance is strong enough that an agent can sequence it correctly.

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