Stage Embody

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

No annotations exist, so the description carries the full burden and does so richly: it discloses what is hidden from inside the view (head, hands, panels, beams, labels), that the Follow runs as usual, that it requires a headset and degrades to embody_skipped outside VR, and the exact error cases. It even lists emitted events (embody_armed, embody_start, embody_stop, embody_skipped), giving exceptional behavioral context.

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?

It is front-loaded with the core purpose and every sentence adds information (modes, hidden elements, reply shapes, errors, events). It is dense and reads as a single run-on block rather than being clearly sectioned, which slightly hurts scanability, but there is little wasted content.

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 complex VR/multi-event tool, the description covers behavior, mode semantics, prerequisites, degradation path, errors, and emitted events. An output schema exists, yet it still clarifies reply shapes ({armed, person, eyes, after}, {inside: true}) without harm, making the definition complete enough to call 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 0%, so the description must compensate; it defines the meaningful values for `when`, `eyes`, and `after`, references `person` and `countdown` explicitly, which is substantial added meaning. However, the required `scene` parameter is entirely undocumented in the description, a notable gap given zero schema coverage.

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 uses a specific verb/resource ('Step the person in VR into a person') and details exactly what happens physically and visually. It clearly distinguishes itself from siblings like stage_actor_follow, stage_perform, and stage_follow by naming how they interact with this command. An agent can tell this apart from any other staging tool without opening a 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?

It enumerates the `when` modes (next/now/off) with explicit behavioral meaning for each, plus the ending conditions (thumbs down, spoken 'stop the performance', or stage_perform(action="stop")). It also points to stage_actor_follow and the person-menu equivalent as alternatives, leaving little to inference.

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