Stage On Air

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

With no annotations, the description carries the full burden and does well: it discloses that the camera goes on air immediately, that the monitor material shows the live camera, that the cut is logged to scenes/<scene>/on_air.jsonl, and that ?onair pages also cut. It also names error conditions (camera not in scene, stage_surface refusals). It stops short of describing what happens to a previously on-air camera or whether the action is reversible.

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 front-loads the core action and every clause carries useful information—monitor behavior, logging, note semantics, page behavior, and errors. It is dense rather than bloated, though the single-paragraph structure with multiple parenthetical cross-references could be easier to scan.

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 mutation tool with no annotations and an output schema already present, the description is largely complete: it covers side effects, logging, monitor material, note usage, page interaction, and error cases. The main gap is the undocumented 'fps' parameter, but otherwise an agent has enough context to call it 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 explains 'monitor' (default 'monitor_screen'; None for none), gives an example for 'note', and ties 'scene'/'camera' to the logging path and error behavior. But it never mentions the 'fps' parameter, leaving one of five parameters undocumented in both schema and description.

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 states a specific verb and resource: 'Cut to a camera: it is on air from now.' It distinguishes the on-air action from related operations like stage_camera_goto or stage_surface by describing the resulting live state, monitor behavior, and logging. It does not explicitly name an alternative to use instead, but the core purpose is clear.

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 through 'the crew's director calls it' and the note about pages opened as ?onair. However, it never explicitly says when to choose this tool over siblings such as stage_camera_goto, stage_view_look_through, or stage_take_start. An agent gets context but no clear exclusions or alternative routing.

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