Reka

index_video

Idempotent

Index a video for search, QA, or full analysis. Processes the video through a pipeline of AI features. Typically takes 3-7 minutes; longer for long videos or the 'full' pipeline. Times out after 10 minutes by default.

Pipelines:

search_only: transcription + captions + embeddings (enables search_videos)
qa_only: transcription + captions (enables ask_video)
full: transcription + captions + embeddings (enables all tools)

Scene detection is enabled by default and produces scene boundaries for get_scenes. Pass scene_detection=False to skip it.

Prerequisites: if using video_id, the video must be in 'uploaded' status. Use get_video to check status before calling this tool.

Input Schema

TableJSON Schema

Name	Required	Default
`pipeline`	No	search_only
`video_id`	Yes
`rationale`	No
`scene_detection`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

TDQS

A4.8/5.0

Behavior5/5

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

The description adds substantial behavioral context beyond annotations: processing times (3-7 minutes), timeout (10 minutes), default scene detection, and the prerequisite that the video must be in 'uploaded' status. It does not contradict the idempotentHint annotation and enriches the operability knowledge.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the primary purpose, followed by essential timing, pipeline breakdown, scene detection note, and prerequisite. It uses clear headers for pipelines and prerequisites, and every sentence adds operational value without fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (multiple pipelines, 4 parameters, defaults, and an output schema), the description covers prerequisites, timeout, pipeline effects, and scene detection. The existence of an output schema means return values need not be described. The description is complete enough for an agent to correctly invoke and handle the tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, but the description fully compensates by explaining the semantics of the pipeline parameter (search_only/qa_only/full), scene_detection (default true, skip with false), and the important 'uploaded' status requirement for video_id. Only the rationale parameter is left unexplained, but that is ancillary.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('Index a video') and the resource, with specific purpose ('for search, QA, or full analysis'). It distinguishes from siblings like upload_video, segment_video, and search_videos by clarifying that this tool builds the index that enables those other tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains when to use specific pipeline types and includes a prerequisite instruction to check video status via get_video before calling. However, it doesn't explicitly state when NOT to use this tool (e.g., if only captions are needed) or mention alternative tools beyond the pipeline a enable relation.

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

All Reka tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.2/5.0

Disambiguation5/5

Each tool targets a distinct purpose: video lifecycle management (upload, get, list, update, delete), group management, content retrieval (transcript, captions, scenes), search, QA, object detection, and metadata exploration. The boundaries are clear, and cross-references in descriptions guide when to use each tool.

Naming Consistency5/5

All tool names follow a consistent verb_noun snake_case pattern (e.g., upload_video, get_transcript, search_videos). The verbs are imperative and descriptive, making the naming uniform and predictable across the entire set.

Tool Count4/5

With 17 tools, the count is slightly above the ideal 3-15 range, but the breadth of features (video upload, indexing, multiple analysis modes, grouping) justifies the number. The tools are well-scoped with no redundancy, though a leaner design might consolidate some retrieval functions.

Completeness5/5

The tool surface covers the full video lifecycle: upload, index, retrieve, search, analyze, update, delete, and group management. Feature catalog and status checking fill any informational gaps, and the workflow guidance (search to find timestamps, then ask or segment) closes potential dead ends.

Resources

Need Help?