spawn_human

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

With no annotations, the description carries the full burden, and it delivers: it discloses that the tool does not reopen the environment USD (preserving edits), can bake an authored NavMesh and wait up to 2000 frames, fails closed when assets/NavMesh are unavailable, enables the extension automatically, and modifies the stage when auto-create-navmesh is used. It also reveals append behavior for reused group names and the 'requires count=1' constraint for rotation. This is exemplary behavioral disclosure.

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 description is dense but well-structured: purpose first, then implementation context, then prerequisites and failure behavior, then sibling-tool guidance, then a consistent Args block. Every section earns its place, and the most critical operational warnings ('Stop the timeline first', 'fails closed') are front-loaded rather than buried.

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 19-parameter tool with no annotations and a 0% schema description coverage, the description is remarkably complete: it covers prerequisites, side effects, failure modes, defaults, and parameter constraints. An output schema exists, so return-value details are not required. The only notable gaps are the undocumented command_id and idempotency_key parameters and the lack of an explicit statement about whether the call blocks until characters are fully spawned or returns immediately, though the 'waits up to 2000 update frames' wording implies blocking.

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, and it largely does: it explains defaults, units, valid values for behavior, relationships like 'patrol_points: Required for patrol' and 'rotation: requires count=1', and coordinate formats. However, two schema parameters, command_id and idempotency_key, are not mentioned in the Args section, leaving a small but real gap in an otherwise thorough parameter explanation.

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 opens with a specific verb and resource: 'Spawn animated NVIDIA human characters into the CURRENT USD stage.' It clearly distinguishes this from sibling tools like list_humans, delete_human, and set_human_behavior by focusing on the act of spawning. The scope ('CURRENT USD stage') is explicitly emphasized, leaving no ambiguity about what the tool does.

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 description gives explicit prerequisites ('A NavMesh is required', 'Stop the timeline first') and names alternatives: 'execute_script remains useful for one-off IRA experiments' and 'reload_script is the better companion for reusable interaction or event logic.' It also clarifies when to choose 'manual' behavior for interaction scripts. This is strong, actionable usage guidance that routes the agent appropriately.

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