Distributed Video QA MCP

Find every time a phrase is said

video_find_phrase

Read-only

Find every transcript segment containing an exact phrase, in time order, to count mentions or locate all places a name or number appears across indexed videos.

Instructions

Every transcript segment containing the exact phrase, in time order. Use it to count mentions or collect every place a name or number comes up; use video_search for meaning rather than wording. A phrase split across two segments is not matched.

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": {
      "phrase": "<phrase>"
    },
    "name": "video_find_phrase"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Most occurrences to return.
`phrase`	Yes	Exact words, case-insensitive.
`video_ids`	No	Limit to these video ids. Omit for every indexed video.

Output Schema

Name	Required	Description
`hits`	Yes	In video then time order.
`count`	Yes	Hits returned.
`phrase`	Yes	What was searched for.
`truncated`	Yes	More occurrences exist beyond the limit.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.0Nov 13, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare the safe read-only, closed-world profile, so the description is not burdened with the safety story. It does add real behavioral context beyond them: results come back in time order, matching is literal wording rather than semantic, and cross-segment phrases are missed. It does not discuss what happens when the limit truncates results.

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?

Three short sentences, front-loaded with the output contract before usage and the edge-case caveat. Every clause carries information an agent would otherwise have to guess.

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?

With an output schema covering return values, full parameter documentation, and annotations covering the safety profile, the description closes the remaining gaps: matching semantics, ordering, and the split-segment limitation. Nothing needed to invoke it correctly is missing.

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

Parameters3/5

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

Schema description coverage is 100%, so phrase, limit, and video_ids are already documented with defaults and bounds. The description reinforces the exact-match semantics of 'phrase' but adds nothing about limit behavior or video_ids scoping beyond what the schema states, so the baseline applies.

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 first sentence names the exact result set ('every transcript segment containing the exact phrase, in time order'), which tells an agent precisely what comes back, not just that it 'finds phrases'. The third clause and the explicit contrast with video_search make it distinguishable from the sibling without opening either schema.

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?

It gives concrete positive use cases ('count mentions', 'collect every place a name or number comes up') and names the alternative with the condition that selects it ('use video_search for meaning rather than wording'). A limitation ('a phrase split across two segments is not matched') prevents a common misuse case.

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