Set up face tracking

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

The description discloses key behavioral traits: it loads a specific engine, starts the timeline, and builds an adapter Script CHOP, which is consistent with the annotations (readOnlyHint=false, openWorldHint=true). It also explains the output format (468/478 landmarks, tx/ty/tz/confidence, nose tip centering) beyond what annotations provide. No contradiction found.

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 two dense but well-structured sentences. It front-loads the primary action ('One-shot face-landmark tracking from a webcam'), includes a practical installation note, lists the build steps, and ends with downstream integration. Every sentence earns its place with no redundancy.

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 (setup with engine load, node creation, data output) and the absence of an output schema, the description covers the essential aspects: what it does, prerequisites, output format, and downstream tools. It could mention naming or access to the created CHOP, but it is sufficiently complete for an agent to invoke successfully.

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 already documents all three parameters with 100% coverage. The description adds semantic value by explaining how num_landmarks relates to the output (468 base vs 478 with iris), and clarifies the tox_path default behavior via the install command. This goes beyond schema descriptions to enhance understanding.

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 a specific verb+resource: 'One-shot face-landmark tracking from a webcam' and details the operational steps (loads MediaPipe engine, starts timeline, builds adapter Script CHOP). It also distinguishes from sibling tracking tools by explicitly focusing on face landmarks and noting downstream usage with bind_to_channel and create_data_visualization.

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 usage context: tracking face landmarks from a webcam, including the prerequisite installation command and the intended downstream tools. It does not explicitly contrast with alternatives like setup_hand_tracking, but the scope is unambiguous enough that an agent can decide when to invoke it.

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