preview_3d_views

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

Annotations declare readOnlyHint=true and destructiveHint=false, so the description doesn't need to restate safety. It adds behavioral details: it outputs a multi-view PNG, includes an enabled grid, legend, and selection summary, and preserves the original camera. However, it doesn't disclose how the single PNG is formatted (e.g., which views are combined) or whether it affects the viewer state beyond the camera, though the readOnly hint covers that. The added details are useful but not exhaustive.

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 is two sentences, front-loading the core function ('Return one labeled multi-view PNG') and then adding key constraints ('preserving the original camera', 'Disable split comparison first'). The additional features (enabled grid, legend, selection summary) are concise and relevant. Only minor waste: the grid/legend details could be considered extraneous, but they add context for what the PNG includes.

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?

The tool has only 2 parameters, 1 required, no output schema, and annotations cover its read-only nature. The description tells the agent what the tool does, prerequisites, and what the output will contain (labeled multi-view PNG with grid/legend/selection summary). It doesn't specify the exact PNG layout or how the presets map to views, but the schema enum provides that. The only missing piece is explicit routing guidance, but for the tool's complexity, it is reasonably complete.

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 0%, meaning the description must compensate for parameter semantics. The description does not mention 'presets' or 'scene_id' at all. However, the schema has clear defaults for 'presets' (['front', 'top', 'isometric']) and the enum list is self-explanatory. 'scene_id' is standard across siblings. Since coverage is 0%, description should have clarified, but the schema is simple and the tool's purpose implies the presets are views to include. This is a partial gap.

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 clearly states the tool's function: to return a labeled multi-view PNG to choose a useful angle, while preserving the original camera. This distinguishes it from siblings like 'capture_3d_view' which likely captures a single view, and from 'navigate_3d_view' which changes the camera. The inclusion of 'multi-view PNG' is specific enough to differentiate it from a simple capture.

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?

The description gives a clear instruction to 'Disable split comparison first' as a prerequisite, but does not explicitly state when to use this tool versus alternatives like 'capture_3d_view' or 'navigate_3d_view'. The context is implied by the tool's purpose (choosing an angle) but no alternative is mentioned. This is a gap in routing.

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