VidLens

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

No annotations provided, so description carries full burden. Discloses key behaviors: returns 'frame/image evidence with timestamps', uses specific AI models (Apple Vision, Gemini), and performance characteristics. Missing safety/auth information and exact nature of auto-indexing side effects.

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?

Dense, information-rich single paragraph. Front-loaded with purpose, followed by technologies, return format, and performance expectations. Bracketed timing notation is efficient. Zero redundant words.

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?

Complex tool with 14 parameters and no output schema. Description adequately covers core search functionality and return types, but fails to explain several parameters (imageFormat, width, dryRun, download options) that affect invocation. Given the parameter richness, additional guidance on the download behavior and dryRun would be necessary for complete coverage.

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 coverage is low (36%), requiring description compensation. Successfully adds meaning to includeGeminiDescriptions and includeGeminiEmbeddings via 'optional Gemini frame descriptions/semantic embeddings'. Also contextualizes intervalSec/maxFrames via timing notes. However, leaves 7+ parameters unexplained including critical dryRun and confusing download-related parameters (autoDownload, downloadFormat) that suggest side effects not mentioned.

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?

Specific verb 'Search' + resource 'visual content of a video or your indexed frame library'. Clearly distinguishes from siblings like searchTranscripts (text) by emphasizing 'actual visual content' and specific technologies (Apple Vision OCR, Gemini).

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?

Provides implicit guidance via performance timing '[~1-3s if indexed, ~60-120s if auto-indexing]', helping decide when to pre-index. However, lacks explicit guidance on when to use vs. findSimilarFrames or extractKeyframes, and doesn't clarify prerequisites like indexing requirements.

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