extract_frames

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

With no annotations provided, the description carries the full burden and does so effectively by detailing behavioral traits: it explains how parameters interact (priority of number_of_frames, caps on exceeding total frames), default behavior, and the output format (list of file paths with UUID filenames). This covers key aspects like mutation (extraction and saving) and response structure, though it lacks details on error handling or performance 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-structured with clear sections (Behavior, Params, Returns), making it easy to scan. Every sentence adds value, such as explaining parameter priorities and defaults, though it could be slightly more concise by integrating some details into fewer sentences without losing 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?

Given the complexity (3 parameters, no annotations, but with an output schema), the description is largely complete. It explains input behaviors, interactions, and output format thoroughly. The output schema covers return values, so the description appropriately focuses on usage and semantics. Minor gaps include lack of error handling or prerequisites, but it suffices for effective tool invocation.

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 0%, so the description must compensate, and it does so comprehensively. It adds meaning beyond the schema by explaining the purpose of each parameter (e.g., 'number_of_frames' extracts evenly across video, 'timestamp_offset' sets interval in seconds), their interactions, and default behaviors, which are not captured in the schema's basic types and titles.

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 with specific verb ('extract frames') and resource ('from a video file'), distinguishing it from siblings like 'extract_audio' or 'clip_video'. It explicitly mentions saving frames with UUID filenames, which differentiates it from tools that might modify or analyze video content without extraction.

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 implies usage through behavioral rules (e.g., defaults to one frame per second if no parameters provided), but it does not explicitly state when to use this tool versus alternatives like 'get_video_metadata' for information or 'clip_video' for segmenting. No exclusions or specific contexts are provided, leaving usage somewhat open-ended.

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