Extract key frames

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral details: it always returns paths, optionally returns inline images for vision clients, and caps those images. It also clarifies the mode semantics (visual cuts vs uniform sampling). No contradictions 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 and front-loaded: the first sentence states the core purpose, followed by a terse but informative line about modes and output behavior. Every sentence earns its place without redundancy, and the structure is easy to scan.

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?

With 8 parameters, only 38% schema coverage, and no output schema, the description is not complete enough. It omits explanations for time-range parameters (start_sec, end_sec), frame limits (max_frames), and the inline_images toggle. The 'capped' mention is vague without a specific limit. While annotations cover safety, the operational details are insufficient for an agent to call this tool correctly without external knowledge.

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 only 38%, and the description does not compensate for the undocumented parameters. It explains 'mode' and touches on output behavior, but parameters like start_sec, end_sec, max_frames, and inline_images have no description in either the schema or the tool description. The agent must infer their meaning, which is a significant gap for a tool with 8 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 clearly states the tool extracts representative JPEG frames via scene-change detection and/or interval sampling, which is a specific verb-resource pair. The modes (scene, interval, both) further clarify functionality, and while siblings like video_get_frame and video_get_frame_burst exist, the scene/interval distinction is unique enough to differentiate without explicit mention.

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 explains the three modes and notes 'both' as default fallback, giving some usage context. However, it does not state when to prefer this tool over siblings like video_get_frame or video_get_frame_burst, nor does it mention exclusions or prerequisites such as dependency checks (e.g., video_check_deps). The guidance is implied rather than explicit.

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