modify_scene

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

With annotations already declaring destructive and open-world behavior, the description adds meaningful context beyond them: it saves once after ordered operations, executes constructors, refuses inherited or instanced edits, and rejects uncertain references. It still omits failure/rollback semantics and permission requirements, but it substantially characterizes behavior.

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 dense and front-loaded: the core batch/save behavior comes first, followed by preview guidance and safety constraints. Every sentence contributes operational information without redundancy.

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 complex batch mutation tool with no output schema, the description covers supported operations, previewing, and key refusal behaviors well. It remains incomplete on parameter structure, per-operation results, and what dryRun returns, which an agent would need for correct composition.

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%, so the description must carry parameter meaning. It mentions dryRun, expectedHash, and the 100-operation limit, but says nothing about projectPath, scenePath, required nodePath fields, or how the operation object fields map to each op type.

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 states a specific verb and resource: applying scene operations in order and saving once. It clearly identifies this as a batch mutation tool by specifying up to 100 operations and listing supported operation categories, though it does not explicitly name sibling alternatives like add_node or set_node_properties.

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?

It explains preview usage with dryRun and notes that expectedHash guards stale previews, which gives clear context for safe invocation. However, it never states when to use this batch tool versus single-operation siblings such as instance_scene, duplicate_node, or set_node_properties.

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