Reframe following a face

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

Annotations only state readOnly=false and destructive=false, so the description adds valuable behavioral context: crop paths are smoothed to avoid snapping, clamped to source edges, and fallback to center crop or fail. This goes beyond the sparse annotations without contradicting them.

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 concise, well-structured, and front-loaded. The first sentence states the purpose, the second paragraph explains key behavior and rationale, and the third provides the workflow. 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 11 parameters and the existence of an output schema, the description covers the core workflow—reframing, face tracking, smoothing, clamping, fallback, and detect_faces integration—well enough for an agent to invoke it correctly. It omits details on some advanced parameters, but the schema partially covers those and the overall picture is clear.

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 64%, and the description adds useful meaning for track_id by explaining it comes from detect_faces. However, it does not compensate for undocumented parameters like sample_fps, max_frames, and min_confidence, which are left without explanation in both the schema and the description.

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 opens with a specific verb and resource: 'Reframe a clip to a new aspect ratio, following a face across the timeline.' This clearly distinguishes it from siblings like detect_faces, blur_faces, transform, and resize_video by combining reframing with face tracking.

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 for when to use the tool ('turning a horizontal interview into a vertical clip') and provides a concrete workflow: call detect_faces first if you want to choose a person, then pass its track_id. It does not explicitly name when-not-to-use alternatives, but the classic-use case and prerequisite are strong guidance.

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