set_semantic_labels

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

With no annotations provided, the description carries the full burden, and it does disclose meaningful behavior: a non-destructive preview mode, an apply (mutating) mode, and read-back verification. However, it omits safety-relevant traits such as the overwrite semantics (default false — does applying when labels exist error, append, or silently no-op?) and the idempotency/command_id execution behavior. This is a partial disclosure for a mutation-capable tool.

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 16-word sentence that packs in the operation modes, API specificity, taxonomy scoping, and read-back behavior. Every element earns its place and the primary verb is front-loaded. There is zero filler.

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 7-parameter tool with 0% schema coverage and no annotations, this description is too sparse. The output schema covers return values, but the agent is left guessing about the meaning of prim_path, the consequences of overwrite, what 'preview' actually returns or changes, and whether the read-back is reflected in the output. Key decisions needed to call the tool correctly are undocumented.

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, but it only hints at three of seven parameters: labels and taxonomy ('labels under one taxonomy') and preview ('Preview or apply'). It gives no meaning for prim_path (the target of the operation), overwrite (a behavior-critical flag), or command_id/idempotency_key (execution control). The burden is not met.

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?

The description names specific verbs ('Preview or apply'), a specific resource ('Isaac Sim 6.0.1 UsdSemantics LabelsAPI labels'), and a clear scope ('under one taxonomy'). It implicitly differentiates from the sibling get_semantic_labels by signaling that this tool writes or stages changes, with read-back confirming the result.

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 'Preview or apply' phrasing implies a sensible workflow — inspect the effect before committing — which gives some usage context. However, there is no explicit guidance on when to prefer this tool over get_semantic_labels, and no exclusion criteria or mention of prerequisites (e.g., prim must exist, stage must be open).

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