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

With no annotations, the description carries the burden of behavioral disclosure. It explains that the tool reads a cache built at upload time, returns source and canvas pixel coordinates, and exposes a 'ready' | 'not-ready' status that hints at cache availability. It does not explicitly say it is side-effect free, but the read-oriented language and cache source strongly imply it.

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?

Every sentence in the description earns its place: purpose, data source, coordinate behavior, use case, and return shape are all covered without redundancy. The most important information is front-loaded, and the return structure is compactly summarized at the end.

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?

There is no output schema, so the description compensates by stating the return shape and the two possible statuses, which is critical for callers. It also clarifies the coordinate-space behavior that would otherwise be ambiguous. The 'bands' field is mentioned but not fully explained, leaving a small gap, so it falls just short of a perfect score.

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 80%, so the schema already documents most parameters. The description adds context about coordinate systems and the meaning of bands, but it does not add significant per-parameter semantics beyond what the schema provides. This aligns with the baseline for high schema coverage.

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 returns horizontal 'safe band' y-ranges and inverse 'text bands', making the resource and output explicit. It also distinguishes itself from the related detect_text_regions tool by framing this as a layout-oriented read operation on the OCR cache.

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 a concrete use case: 'Use to lay out captions, titles, callouts so they never collide with the video's own text.' It references detect_text_regions as the source of the OCR cache, which implies when that tool matters, though it does not explicitly state when not to use safe_zones or exhaustively list alternatives.

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