set_usd_edit_target

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

Annotations already declare readOnlyHint=false, destructiveHint=true, and idempotentHint=true. The description adds real value by disclosing that subsequent mutations are redirected to the chosen layer rather than the root, which explains the destructive/idempotent profile. It does not, however, explain any persistence implications of the target change or what happens to layers that are muted or isolated.

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 compact sentences with the behavioral effect front-loaded, followed by the return shape. The 'Returns:' block is genuinely useful since no output schema exists, though the '(mutations after this call...)' parenthetical slightly restates the first clause.

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 two-parameter tool with no output schema, the description covers purpose, post-call effect, and the exact return object, which compensates for the missing output schema. The remaining gap is persistence semantics (whether the edit target survives a stage save), which an agent doing multi-step USD authoring could want.

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 both stage_name and layer_index (including the 0-based index and the root default) are already fully documented in the schema. The description only echoes the concept of a 'chosen layer' and 'root', adding no format or indexing detail beyond the structured data, 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?

The description gives a specific verb+resource: it points the stage's edit target at a chosen layer in the stack, and explains the operational consequence ('mutations after this call land on the chosen layer, not the root'). That clearly distinguishes it from adjacent USD tools like insert_usd_sublayer, mute_usd_layer, and isolate_usd_layer, though it doesn't name any of them explicitly.

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?

Usage is implied rather than stated: the sentence 'mutations after this call land on the chosen layer, not the root' tells the agent when the call matters, but there is no explicit guidance on when to switch layers, when not to, or how to revert to the root target beyond the schema's default note.

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