Make a network react to body pose

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

Beyond the annotations (readOnlyHint=false, openWorldHint=true), the description discloses side effects: it creates a fresh baseCOMP with a Select→Math→Hold→Filter→Limit→Rename chain merged into null_out, exposes a Reactive custom page, writes expression-mode binds with failures as warnings, and emits a warning for constant tz. This exceeds what annotations alone convey and adds valuable behavioral context.

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 but every sentence earns its place, covering purpose, pipeline, metrics, bindings, controls, and a data-quality warning. It is front-loaded with the main purpose and flows logically. For a tool with 8 parameters and complex behavior, this length is appropriate and well-structured.

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?

The description is highly complete given the tool's complexity: it explains the whole workflow, the output structure, the supported metrics, the bindings behavior, the exposed controls, and the critical MediaPipe 2D-landmark caveat. Even without an output schema, the agent knows what to expect (a Null CHOP with channels and a Reactive page). No gaps are evident.

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 100% and individual parameter descriptions are already detailed, so the baseline is 3. The tool description adds extra meaning by explaining the internal processing chain (Select→Math→Hold→Filter→Limit→Rename), the exact behavior of bindings (expression-mode, same shape as bind_to_channel, warning instead of throw), and the reliability caveat for z/angle/velocity metrics. This supplements the schema rather than merely repeating it.

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 clearly states the tool's function: it takes a 33-sample MediaPipe pose CHOP and derives scalar reactive channels (right-hand height, distance, angle, velocity, etc.) into a Null CHOP. It explicitly distinguishes itself from bind_audio_reactive and references setup_body_tracking, providing a specific verb+resource+output structure.

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 gives clear context when to use the tool (body-pose reactivity) and prerequisites (run setup_body_tracking first). It implies alternatives by naming bind_audio_reactive and warns about unreliable metrics, but does not explicitly list when not to use it versus other body-reactive tools. This is strong but not fully explicit about exclusions.

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