Any Video to Text

Ask about a video

ask_video

Answer one question about a public video, using only what is said in it. Returns the answer, whether the transcript covers the question, and up to 3 timestamps. If the video has not been transcribed yet it is transcribed first (same cost and waiting as get_transcript, so it may answer that it is still running with a jobId; then call transcribe_status and call ask_video again). Free accounts get a few questions per day. Questions aren't stored.

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": {
      "url": "<url>",
      "question": "<question>"
    },
    "name": "ask_video"
  }
}

Input Schema

Name	Required	Description
`ai`	No	true to use the AI version of the transcript, when list_my_transcripts or get_my_transcript says the saved one is AI.
`url`	Yes	Link to one public video: a TikTok, YouTube (including Shorts), Instagram Reel/post, Facebook or X video URL.
`history`	No	Earlier questions and answers in this chat, oldest first, for follow-up questions. Only the last 3 are used.
`question`	Yes	The question, up to 500 characters.

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 6, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Goes well beyond the annotations, which only declare openWorldHint and non-idempotency: it discloses the return shape (answer, transcript-coverage flag, up to 3 timestamps), the async jobId/two-call flow on first use, the wait cost relative to get_transcript, a free-tier rate limit, and that questions are not stored. That is exactly the context an agent needs before calling a tool with hidden transcription 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.

Conciseness4/5

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

Front-loaded with purpose and return values, then the failure/retry flow and quota caveat, with no filler sentences. The nested parenthetical about jobId is slightly dense but every clause carries operational information.

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 no output schema, the description fully enumerates return values, and it also covers the asynchronous first-run case and quota limits. Nothing an agent needs to invoke it correctly or interpret an 'still running' response 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 url, question, history (last 3 used) and ai are already documented in the schema. The description adds only the 'one question' framing and the fact that history is for follow-ups, so it sits at the baseline rather than adding new parameter meaning.

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 a specific verb and resource ('Answer one question about a public video') and constrains the answer source to 'only what is said in it', which separates it from summarize_video and get_transcript. The scope is precise enough that an agent can route to it without opening the schema.

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?

Gives a clear conditional flow: if the video is untranscribed it handles that first, may return a jobId, then the agent should call transcribe_status and re-call ask_video. It also implies one-question-per-call and mentions cost parity with get_transcript, but never explicitly states when to prefer get_transcript or summarize_video over this tool.

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

All Any Video to Text tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?