select_3d_region

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

Annotations are minimal (readOnlyHint=false, openWorldHint=false, destructiveHint=false) and the description does not contradict them. It adds substantial behavioral context: the selection is reversible, it replaces prior selections, it has a highlight option, and it does not perform automatic segmentation. This goes well beyond the annotations and fully discloses the tool's side effects and constraints.

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 a single dense paragraph of about 90 words. It front-loads the primary purpose, then adds behavioral notes. While it could benefit from bullet points for readability, every sentence contributes information and there is no fluff. It is concise given the tool's complexity (12 parameters) and well-structured logically.

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 description is largely complete for an agent to use the tool correctly. It covers the selection criteria, reversibility, replacement behavior, point-cloud constraint, label ID caveat, and preview/highlight options. It lacks explicit detail on the return format (though 'PNG preview' is mentioned) and does not enumerate all parameters, but given the absence of an output schema and the tool's complexity, it provides sufficient context to avoid misinvocation.

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, the description must compensate. It explains key parameter semantics: bounds corresponds to the world box, plane to the halfspace, values to scalar field intersections, and object_index to the object. It also mentions highlight (disable to preserve colors) and action (clear restores visibility). While not every parameter (e.g., detail, focus, isolate) is individually described, the core selection modes and critical options are covered, providing meaningful value beyond 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 clearly states the tool's purpose: to select/isolate/focus points in a 3D scene with one step, offering multiple selection criteria (object, scalar field, world box, plane halfspace). It distinguishes itself from sibling tools like manage_3d_selections by emphasizing the 'one-step' and 'replaces previous selection' nature, making it obvious when to use it.

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 provides explicit usage guidance: it explains that selection is reversible ('clear restores prior visibility'), warns that label IDs are numeric (not semantic), notes the point-cloud-only limitation, and clarifies that it replaces the previous selection. While it doesn't explicitly name alternatives, it implies usage through phrases like 'one-step' and contrasts with more complex selection management, giving clear context for when to use it.

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