node_manage

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

With no annotations, the description carries full burden. It discloses key behaviors: delete is undoable, cannot delete/duplicate scene root, rename has collision and character restrictions, reparent cannot move into descendants, and scene_file guard triggers EDITED_SCENE_MISMATCH. It also explains the canonical call shape and compatibility alias, offering rich behavioral context beyond the schema.

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 long due to nine ops, but it is organized with headers, bullet lists, and a clear canonical call shape. Every sentence adds operational value—no filler. The structure makes it easy to scan and parse.

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?

Addresses all ops, constraints, error conditions, read vs write behavior, resource forms, and call syntax. An output schema exists (likely for op results) but the description still covers return info for get_children and get_groups. For a complex multi-op tool with no annotations, this is comprehensively 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 coverage is 0%, so the description must define parameters. It lists the argument signature for every op (e.g., 'delete(path, scene_file="")') and explains the scene_file guard. However, it does not describe session_id's purpose beyond being 'top-level', and type details for path/index are inferred from naming rather than explicitly stated. This is a minor gap given the complexity.

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 opens with 'Node tree manipulation' and enumerates specific verbs (delete, duplicate, rename, reorder, reparent, groups) plus hierarchy reads. This clearly distinguishes it from sibling tools like node_create (creation), node_set_property (property changes), and node_find (search).

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 states a preference for resource forms during active-session reads and lists all ops explicitly. It does not explicitly contrast with sibling tools (e.g., 'use node_create for new nodes'), but the op list clearly implies the scope. The scene_file guard guidance adds usage context. A minor gap is lack of explicit when-not-to-use guidance.

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