Video Storyboard

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

Annotations already declare the non-mutating, non-destructive, non-idempotent profile, so the bar is lower, but the description adds almost nothing beyond them or the schema. It doesn't mention the 120-second window limit, the ~16-tile cap, the sha256 source verification, or what artifact is produced, leaving the key behavioral constraints undisclosed.

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?

A single short sentence with the core action front-loaded and no filler. It is appropriately sized, though the cryptic phrasing reduces the value of the brevity.

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?

An output schema exists and the input schema is fully documented, so return values needn't be explained. However, for a tool with nested constraints (window, tile count, hash verification) and multiple frame-producing siblings, the description omits the constraints and routing an agent would need to call it 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?

Schema description coverage is 100% and the nested request object documents rows, columns, pixel limits, time ranges, and hash verification, so the schema carries the parameter burden. The description adds no parameter-level meaning (e.g., how rows/columns map to tiles), which is the baseline-3 case.

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 verb+resource (create a storyboard) is identifiable, but the qualifiers 'measured source' and 'literal absolute source-clock labels' are opaque jargon that don't clarify what a storyboard actually is (a grid of sampled frames with timestamps burned in). It also does nothing to distinguish this from siblings like video_frames, video_detect_scenes, or video_clip_select, which also produce frame samples.

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?

No when-to-use, when-not-to-use, or alternative is stated. An agent cannot tell whether to reach for this versus video_frames, video_detect_scenes, or media_perceive; the description offers no routing signal at all.

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