rig_turn

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

With no annotations, the description carries the full burden and does disclose real behavior: face_slot is converted to a mesh, a `turn_test` animation is added as a side effect, and feature depth sign conventions are explained. It stops short of stating whether existing mesh/animation data is destroyed or what permissions/project state are required.

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?

Front-loaded with the core concept, then a compact behavioral note and a dense but useful feature-depth table. Some sentence fragments ('features {slot: depth}: nose 1.25...') trade grammar for density, but nearly every token carries information.

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 7-parameter, nested-object tool with zero schema coverage and no output schema, the description explains the conceptual model and the features map well but leaves half the parameters (turn_range, swap_pairs, pitch, head_bone) undefined. An agent could call it, but would be guessing on several arguments.

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 compensate, and it does strong work on the hardest parameter: `features {slot: depth}` with concrete example values and the negative-depth convention for parts behind the head. But face_slot is only incidentally explained, and head_bone, project, pitch, turn_range, and swap_pairs get no semantics at all.

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 and resource: rigging a 2.5D head turn driven by one control bone (turn_ctrl). The mesh-behavior sentence ('middle travels with the control while its outline stays pinned') pins down exactly what the tool produces, distinguishing it from siblings like rig_face or rig_mesh.

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 final sentence gives post-rig usage ('Animate turn_ctrl's translate to turn') and the features list implies the slot-to-depth input convention. However, there is no explicit when-to-use vs alternatives routing (e.g. versus rig_face or rig_biped head handling), so usage is only implied.

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