Stage Capture

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

No annotations exist, so the description carries the full burden, and it does disclose important traits: asynchronous "replies at once with the job", isolation from the live link and scene files, and the exact output path/format. However, it omits cost/duration expectations, concurrency limits on the GPU slot, and what happens on failure or to an already-running job, which are material for a long render.

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 and every clause carries real information, but the opening sentence is a run-on and the whole body is a dense multi-topic block that an agent must parse linearly to find a given parameter. Restructuring into labelled groups (camera, timing, setup, output, control) would cost nothing and help selection.

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 asynchronous render tool this is unusually complete: it states the async contract and status follow-up, the isolation guarantees, the output artifacts, and the override semantics of setup commands. With an output schema present it correctly does not spend words on return values.

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?

With 0% schema description coverage across 19 parameters, the description compensates heavily: it defines t0/t1 as song seconds, the four mutually exclusive camera modes with their shapes and Blender coordinate/lens conventions, size, clock/clock_at, setup command forms with worked examples, sets, audio, keep_frames and video. Gaps remain for name, scenes and the fps default, which are never explained.

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 first sentence gives a specific verb and resource ("Capture the stage on the PC, frame-locked") and immediately defines the semantics of frame n vs song time. It is distinctive enough to separate it from siblings like stage_take_view or stage_camera_record, though it never names an alternative 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?

It clearly frames the usage context: background, headless, GPU slot, no headset, no interference with the live stage, plus the required follow-up via stage_capture_status(scene, job). That tells the agent when this is appropriate, but it does not compare against sibling capture/render tools or state when not to use it.

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