Stage View Snapshot

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

With no annotations, the description carries the full burden and does it well: it discloses the file destination, the desktop VR resolution/shape difference (16:9 frame vs 1024 px square), the tag naming rules, the specific failure case (hidden or minimised tab with no size), and explicitly says 'Emits: nothing'. It stops short of stating permissions or whether the capture is synchronous/blocking.

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?

Front-loaded with the action and destination, and telegraphic throughout with zero filler sentences. The return-payload enumeration is somewhat redundant given an output schema exists, though the caveats about 'canvas' not surviving JSON and pose being unset for eye shots are genuine semantics rather than restatement.

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?

An output schema exists, so the reply-shape detail is a bonus rather than a necessity, and the description still covers mode differences, tagging, save location and the one known error. What's missing is timing/synchrony and any dependency on view state (e.g. must a camera be looking through before a desktop shot).

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% and the single 'scene' parameter has no schema description, so the description must compensate — it does by showing 'scenes/<scene>/snapshots/', which tells the agent the parameter selects the scene directory the PNG lands in. Indirect, but sufficient for a one-parameter tool.

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?

States a specific verb and resource ('Save a PNG of what the person sees') plus the exact destination path, and names the underlying page command 'snapshot'. The desktop/VR branching makes the output artifact concrete enough that an agent can distinguish it from siblings like stage_capture or stage_take_view.

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 by the mode breakdown (desktop vs VR, camera vs editor vs eye), but there is no explicit statement of when to call this instead of the many adjacent capture tools (stage_capture, stage_capture_status, exam_picture_score, stage_take_view). Error conditions are mentioned, which helps, but the selection guidance is left to inference.

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