video_frames

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

With no annotations provided, the description must carry the full behavioral burden. It discloses that remote videos are fetched once at <=720p and cached, that frames are model-visible images, and that there is a 12-frame cap per call. It does not explicitly state read-only status or potential failure modes, but the disclosed behaviors are substantial and honest, covering key operational constraints such as caching and resolution limits.

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 well-organized: a one-line purpose, a contextual note, usage modes, a constraint, then a clean Args block. Every sentence adds value—no fluff or repetition. The front-loaded purpose and usage guidance make it easy to skim, and the parameter documentation is compact yet complete.

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 tool's complexity (7 parameters, various time formats) and lack of an output schema, the description covers the essential details: how to specify frames, window constraints, and output form ('model-visible images'). It leaves out exact return structure (e.g., whether images are markdown or base64) and error handling, which could matter for an agent, but overall it provides enough to use the tool confidently for typical video-frame extraction tasks.

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 has 0% parameter descriptions, so the description completely compensates by providing a detailed Args section. Each parameter gets a purpose, default where applicable, and format examples (e.g., '0:05, 1:30, 95.5' for timestamps, 'seconds or MM:SS' for start/end). This fully bridges the gap left by the schema and makes the tool callable correctly with minimal agent effort.

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 states a clear purpose: 'Extract frames from a video and return them as model-visible images.' It uses a specific verb and resource, and adds the contextual hint 'This is how you SEE a video's content,' which distinguishes it from video_clip (creating a clip) and video_transcript (text extraction). An agent can immediately understand what this tool does and why it exists alongside media tools.

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 two usage modes: explicit 'timestamps' or uniform sampling via 'count' with optional start/end window. It also clearly states the 12-frame cap and advises making additional calls for more coverage. However, it does not explicitly mention when to prefer this tool over alternatives like video_clip or media_probe, so it lacks an explicit 'when-not-to-use' exclusion. Still, the internal guidance on parameter selection is strong.

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