get_frames

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

Annotations already indicate the tool is read-only, idempotent, and non-destructive. The description adds valuable behavioral details: extraction modes, default behaviors, limits (maxFrames up to 60), and output format (optimized, deduplicated JPEG frames). No contradictions.

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 concise, well-structured with two bullet points for modes and a list of supported sources. Every sentence provides value without 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 moderate complexity and absence of output schema, the description covers the core functionality well. It explains input, modes, and output format. However, it could specify how frames are returned (e.g., URLs vs. base64) to be fully complete.

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?

The input schema descriptions cover most parameters. The description adds context beyond the schema by explaining the difference between scene-change detection and dense sampling, and the effect of the threshold parameter.

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's purpose: extracting key frames from a video URL. It specifies two extraction modes and lists supported sources, making it distinct from sibling tools like get_metadata or get_transcript.

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 two modes and their defaults, and lists supported sources. However, it doesn't explicitly guide when to use this tool versus alternatives like get_frame_at (for specific timestamps) or get_frame_burst (for fixed intervals).

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