segment_scene

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

The description discloses one behavioral trait: 'Rebuilds the scene graph,' implying a mutating operation. However, with no annotations provided, it fails to state whether existing scene objects are destroyed, whether the operation is undoable, what happens if the mesh is not loaded, or any permission requirements. These are significant gaps for a mutation tool.

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 short sentences with no wasted words; the action is front-loaded and the example is placed early. The structure is efficient and scannable, though the meaning of 'given names' could have been clarified without bloating the text.

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 return field list may be documented externally. However, the description misses crucial context: how to determine valid names, the prerequisite of a loaded mesh, relationship to get_scene_info for read-only access, and side-effect risks. This is insufficient for safe, correct invocation.

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 zero schema description coverage, the description must clarify the 'objects' parameter. It provides an example (['chair', 'table']) but does not explain what these names refer to (e.g., labels in the source mesh, arbitrary names to assign), valid constraints, or error behavior for unmatched names. The semantics remain ambiguous.

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 ('segment') and resource ('loaded mesh') with a clear goal: producing editable objects for named targets. The example adds concrete context, and the side effect of rebuilding the scene graph distinguishes it from sibling tools like add_object, remove_object, or get_scene_info.

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?

No explicit guidance on when to use this tool versus alternatives. It mentions the 'loaded mesh' prerequisite but does not instruct the agent to ensure load_scene was called first, nor does it warn that get_scene_info should be used instead when only scene information is needed without modifying the graph.

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