Blur faces

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

The description goes beyond annotations by detailing behavioral traits: per-face tracked blur regions, expanded boxes to cover hair/chin, and a critical warning that a missed detection leaves a face unblurred, advising review of output. This adds meaningful context beyond the readOnlyHint=false (write operation) and destructiveHint=false annotations. It does not mention output path behavior or error handling, but those are partially covered in the parameter schema.

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 three short paragraphs, front-loaded with the core action, followed by behavior details and a safety note. Every sentence earns its place: the tracking explanation, the box expansion, the exclude_primary use case, and the review warning. No filler or 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 (10 parameters, encode settings, output schema), the description covers the essential behavior and a critical risk (missed detections). It does not explicitly mention that encode settings apply or that output is a file, but these are implied by the schema and output_path parameter. The description is nearly complete for a privacy-blurring tool.

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 70%, so many parameters already have descriptions. The narrative adds extra context for exclude_primary (street interviews) and expand (hair/chin coverage), but does not explain max_frames or sample_fps, which lack schema descriptions. Overall, the description adds some value beyond the schema but does not fully compensate for the uncovered parameters.

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: 'Blur every face in a clip', and then explains the tracking behavior ('following each one as it moves'). This clearly distinguishes it from sibling tools like detect_faces (detection only) and track_and_crop (cropping). The purpose is unambiguous and specific.

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 implies usage (blurring faces in video) and gives a contextual example ('the usual requirement for street interviews' for exclude_primary). It also warns to review output before publishing. However, it does not explicitly state when to prefer this tool over alternatives (e.g., detect_faces) or what situations are unsuitable. This is adequate but lacks direct usage exclusions.

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