pro_visualize_scene

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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description adds genuinely useful context beyond them: 'Does not save' clarifies the mutation is session-scoped, and dry_run=true is documented as a non-mutating inventory of current scene and light names. What it does not disclose is which existing values get overwritten when configuring (floor settings, background mode), so it stops short of a 5.

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?

Three tight sentences with the capability statement front-loaded, followed by the two most operationally important caveats (dry_run behavior, no save). No filler. Density of jargon makes it slightly harder to parse than ideal, but nothing is wasted.

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 12-parameter, destructive, conditionally constrained tool with no output schema, the description should explain the background_type/plain/gradient RGB interplay and what the agent gets back from an inspection. It covers the core scene/HDRI/light story adequately but omits the background-mode family and any return-value characterization, leaving real gaps.

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 only 33% across 12 parameters, so the description has to carry weight. It meaningfully covers dry_run, scene/HDRI paths, environment rotation, floor shadows/reflections, and named lights, but leaves background_type, background_top_rgb/background_bottom_rgb, disable_light_ids, and document_path semantics unaddressed despite the intricate conditional rules in the schema.

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 gives a specific verb pair ('Inspect or configure') and enumerates the exact resource surface: native scene/HDRI, environment rotation, floor shadows/reflections, and named lights, anchored to 'the exact saved model'. That is far more precise than a restated name. It does not, however, name any sibling (e.g., pro_visualize_appearances or pro_visualize_camera) to draw the boundary, which keeps it below a 5.

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 'Inspect or configure' plus the dry_run inventory mode, so an agent can infer read-before-write workflow. The closing line 'Visualize fidelity requires a rendered check' implicitly routes verification to a render tool rather than this one. There is no explicit when-not guidance or named alternative, so it sits at implied-usage level.

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