Distributed Video QA MCP

Remove a video from the index

video_delete

DestructiveIdempotent

Delete a video's transcript, frames, and vectors, including the server's downloaded copy and extracted frames, while leaving your original path-ingested file untouched.

Instructions

Delete a video's transcript, frames and vectors. A file you ingested by path is never deleted; only the server's own downloaded copy and extracted frames are.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "video_id": "<video_id>"
    },
    "name": "video_delete"
  }
}

Input Schema

Name	Required	Description	Default
`video_id`	Yes	Video id from video_list or an ingest result.
`delete_files`	No	Also delete the server's downloaded copy and frames.

Output Schema

Name	Required	Description
`removed`	Yes	False when it was not in the index.
`video_id`	Yes	The video removed.
`files_deleted`	Yes	Whether the server's own media copy and frames were deleted.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.0Nov 13, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already flag destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description adds genuinely non-obvious context beyond that: the user's source file at the ingested path survives, and only the server's downloaded copy and extracted frames are removed. It stops short of stating whether deletion is reversible or what happens for a nonexistent video_id.

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?

Two sentences, no filler, with the destructive scope front-loaded and the important caveat second. Every clause carries information an agent needs before invoking a destructive call.

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?

With an output schema present, return values need no explanation, and annotations plus full schema coverage carry the rest. The only residual gap is edge-case behavior — deleting an already-deleted or unknown video_id — which is minor but unaddressed for a destructive operation.

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 coverage is 100%, so the baseline is 3, and the description slightly exceeds it by clarifying the consequence of delete_files — the ingested-at-path original is explicitly untouched. It does not add format or syntax detail for video_id beyond the schema's 'video id from video_list or an ingest result'.

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 opens with a specific verb and scope: 'Delete a video's transcript, frames and vectors', enumerating exactly which artifacts are removed. This is unambiguous and cannot be confused with read-side siblings like video_search or video_info.

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

Usage Guidelines3/5

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

Usage is implied by the destructive framing but never stated explicitly; there is no 'use this when…' guidance and no reference to alternatives such as re-ingesting or checking video_info first. The one real boundary it draws — ingested-by-path files are never deleted — is a behavior fact rather than a when-to-use rule.

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