skeleton_manage

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It describes mutating actions (set_bone_pose, scaffold_ragdoll) and inspection (get_skeleton_info), but it does not state side effects (e.g., whether set_bone_pose overwrites existing transforms, or whether scaffold_ragdoll replaces existing physics nodes). It also doesn't mention error behavior or whether operations require a selected Node. This is a moderate gap for a multi-op 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?

The description is well-structured: a brief summary line followed by a bulleted list of ops. Each op is one line with parameter hints. It front-loads the tool's purpose and separates ops clearly. The only slight redundancy is the final paragraph about call shape and 'op' handling, but that is necessary because the schema is loose. No waste.

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?

Given the tool's complexity (multiple ops, nested params, no schema details), the description is quite thorough. It covers all ops, parameter names, and the call format. However, it misses details like return values for each op (though an output schema exists), prerequisites (e.g., that a Skeleton3D node must be selected), and edge cases (e.g., what happens if bone_name doesn't exist). These are moderate gaps but not critical for an agent to call the tool correctly.

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 schema provides no meaning for the 'op' enum values or the 'params' object. The description fully compensates by documenting each op's parameters inline (e.g., skeleton_path, bone_name, position, rotation, scale for set_bone_pose; collision_layer, total_mass for scaffold_ragdoll). It also clarifies the 'params' structure and the canonical call shape, which is essential given the schema's ambiguity.

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 starts with a clear summary: 'Skeleton3D Rigging, Bone Transform Inspection, BoneAttachment3D Sockets, and Ragdolls.' Then it lists four concrete operations, each with a specific verb and resource (e.g., 'get_skeleton_info' for inspection, 'set_bone_pose' for transform changes). This distinguishes it from siblings like 'joint_manage' or 'body_manage' by clarifying it deals with Skeleton3D bones and attachments.

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 clear guidance on what each op does, including the context for using 'scaffold_bone_attachment' (to attach a node to a bone) and 'scaffold_ragdoll' (to generate PhysicalBone3D nodes). However, it does not explicitly state when not to use this tool versus siblings, nor does it mention alternatives. The ops' purposes are clear enough that an agent can infer use cases, but explicit exclusion of, say, 'joint_manage' for physics joints would improve it.

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