Scene Viewport Snapshot

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

Annotations already cover the safety profile (read-only, idempotent, non-destructive), so the bar is lower, yet the description adds real context: the GUI-only constraint, the specific error surfaced in headless mode, and the forced refresh that guarantees a current frame. It stops short of describing the return envelope, but the WYSIWYG/HUD caveat is a genuinely useful 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?

Front-loads the action in the first line, then qualifies with the GUI constraint. The 'That is a feature' sentence is slightly editorial but earns its place by preempting an agent wondering why HUD/ornaments appear in the shot.

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 4-parameter, zero-required capture tool with full schema coverage and no output schema, the description covers the key operating constraint and the composition of the returned image. It is close to complete; only the return/pagination envelope and sibling routing are unstated.

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 100%, so format, quality and max_size are already fully documented with defaults and trade-offs. The description adds nothing about parameters, which is the correct baseline-3 outcome when the schema carries the load.

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 (capture the active viewport as an image) with a clear WYSIWYG qualifier. It does not differentiate itself from close siblings like scene_snapshot or scene_render_preview, leaving the agent to infer which capture tool fits which case.

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?

Names a definite when-not condition: GUI sessions only, with headless sessions returning a gui_session_required error. It does not name an alternative for clean/render captures (e.g. scene_render_preview), so routing among the snapshot siblings is still left to inference.

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