Skip to main content
Glama
reka-ai

Reka Vision MCP Server

Official
by reka-ai

segment_video

Read-onlyIdempotent

Detect objects in a video segment using text prompts. Get per-frame bounding boxes and confidence scores for any uploaded video without needing feature indexing.

Instructions

Detect objects in a video segment using text prompts. Describe what to look for and get per-frame detections with bounding boxes and confidence scores.

Prompt tips:

  • Use broad, visual categories: 'animal', 'vehicle', 'person', 'text on screen'

  • Specific labels ('rabbit', 'Toyota') are less reliable — the detector matches visual patterns, not semantic concepts

  • Best for confirming whether a category of object appears in a time window, not for precise identification

How to pick a time range:

  • Use search_videos to find WHEN something appears, then pass those timestamps here

  • Use get_scenes to scan systematically — call segment_video once per scene (scenes typically fit in the 15s window)

  • Or pass any range you already know

Maximum range is 15 seconds per call; for longer spans, make multiple calls with consecutive windows.

Does NOT require any feature indexing — works on any uploaded video.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
endNo
startYes
promptsYes
video_idYes
rationaleNo
thresholdNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.10

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already mark readOnly and idempotent; description adds behavioral detail beyond that: per-frame outputs, prompt reliability caveats, 15-second maximum range, and no requirement for feature indexing. No contradiction with annotations.

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?

Well-structured with clear sections for prompt tips and time-range selection; every sentence adds value. Front-loaded with the core purpose before implementation guidance.

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

Completeness4/5

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

Covers the core usage workflow, constraints, and output nature, and an output schema exists to fill in return-value details. Missing semantics for the optional threshold and rationale params, but defaults and the rest of the description make the tool safely callable.

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

Parameters4/5

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

Schema description coverage is 0%, so the description carries the burden. It explains prompts (broad categories vs specific labels) and time-range semantics (15-second windows, consecutive calls), but leaves threshold and rationale parameters undocumented. Partial compensation.

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?

States specific verb and resource: 'Detect objects in a video segment using text prompts' and clarifies output as per-frame detections with bounding boxes and confidence scores. This distinguishes it from sibling video tools like search_videos or get_scenes.

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

Usage Guidelines5/5

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

Provides explicit when-to-use guidance: best for confirming object category presence, not precise identification. Gives a clear workflow with search_videos and get_scenes, plus the 15-second call limit and multi-call strategy.

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