Create pose tracking

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

Annotations only state readOnly=false and destructive=false. The description adds value by revealing it creates two CHOPs, includes smoothing and mirror features, and that the synthetic source requires no camera or plugin. It also notes the free MediaPipe plugin dependency for real tracking. Does not mention potential overwriting, but annotations already cover destructiveness.

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?

Four sentences, densely packed with purpose, outputs, source options, features, and downstream integration. Every sentence earns its place, and the description is front-loaded with the primary purpose. No filler or tautology.

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 tool with 8 parameters and no output schema, the description is remarkably complete: it explains core function, data structure (33 landmarks, tx/ty/tz/confidence, keypoints examples), source variants, default behavior, and downstream use. It gives an agent everything needed to invoke the tool and set expectations.

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?

The input schema provides detailed, 100% coverage for all 8 parameters. The description adds no new parameter-level semantics beyond echoing the synthetic default and source enum. Baseline 3 is appropriate since the schema handles the heavy lifting.

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?

Clearly states it sets up full-body pose tracking and describes the produced outputs (canonical pose CHOP and keypoints CHOP). It distinguishes itself as the foundation for body-reactive visuals, explicitly naming downstream tools (create_pose_skeleton, create_body_reactive) and contrasting with extract_audio_features.

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?

Provides strong usage context: it is the foundation for body-reactive visuals, and the output feeds into create_pose_skeleton or create_body_reactive. Also explains when to use the synthetic default (no camera/plugin) versus mediapipe, osc, or existing_chop. Lacks explicit exclusions, but the guidance is clear and actionable.

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