Video Frames

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

The description adds real behavioral context beyond the annotations: no similarity pruning, no OCR, sheet tiles carry actual source times/digests, and scene/keyframe sampling may miss short events. However, annotations set readOnlyHint=false and idempotentHint=false for what reads as an inspection operation, and the description does nothing to explain that discrepancy or what output is produced.

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?

Five short sentences with no filler, and the mode/constraint guidance is reasonably front-loaded. But the terseness shades into opacity ('without a watched claim', 'Selection retains changed text') rather than efficient clarity.

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 so return values need not be explained, and the annotations cover the safety profile. Still, for a nine-parameter, five-mode media tool, the description leaves key operational questions (default behavior, mode trade-offs, relationship to sibling tools) unanswered.

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%, so the schema already documents all nine parameters, establishing a baseline of 3. The description only loosely reinforces two of them ('narrow window' -> start/end_seconds, 'explicit FPS' -> fps) without adding format or constraint detail the schema lacks.

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 phrase 'Inspect a bounded burst/window or timestamped contact sheet' gestures at extracting frames from a video, and the mode enum (frames/sheet/filmstrip/scenes/keyframes) clarifies intent. But the wording is jargon-heavy ('bounded burst/window', 'watched claim') and never plainly states 'extract frames from a video file', nor does it distinguish this tool from close siblings like video_frame, video_storyboard, video_detect_scenes, or video_frame_by_query.

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?

Only 'Dense filmstrips require a narrow window and explicit FPS' offers actionable guidance, and it is scoped to one mode. There is no when-to-use/when-not guidance and no routing to any of the many sibling frame/scene/dedup tools, leaving the agent to guess which one applies.

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