Detect faces

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

Discloses that the tool downloads and caches a model on first use and requires the 'vision' extra. It also describes the output format (pixel and normalized coordinates, tracks) which adds transparency beyond the annotations. No contradiction with annotations.

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 compact yet informative, front-loading the main purpose and then expanding on output and usage. Every sentence adds value without 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 (6 params, output schema), the description covers purpose, output, sampling behavior, and dependencies. It is complete enough for an agent to select and invoke correctly.

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 schema already documents all parameters clearly, and the description adds extra context—e.g., sample_fps tuning advice and the max_frames safety cap. This goes beyond the schema descriptions, enhancing 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 starts with 'Find faces in a video, sampled over time,' clearly stating the action and resource. It further distinguishes itself from siblings like blur_faces or detect_scenes by detailing the output (bounding boxes, tracks). This is a specific verb+resource combination with strong differentiation.

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 practical guidance on sample rates ('2 fps is usually enough to follow a talking head; raise sample_fps for fast movement') and prerequisites ('Needs the vision extra'). It does not explicitly name alternative tools, but the context is sufficient for most use cases.

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