Real Alpha

Read a minute of an episode

transcript_excerpt

Read-onlyIdempotent

About a minute of an episode's transcript, from a second into the video, for an episode Real Alpha cut: the lines with their times and, where the transcript says, who is talking, plus the link that plays the episode from there. Use it to check the exact words around a moment's quote (a moment's episode_url has the video id and second). Only the episodes Real Alpha cut have a transcript, never more than about a minute of one at a time, and a machine transcript can misspell names.

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": "<video>",
      "second": "<second>"
    },
    "name": "transcript_excerpt"
  }
}

Input Schema

Name	Required	Description	Default
`video`	Yes	The YouTube video id, like "dQw4w9WgXcQ", or a realalpha.app/v/ or YouTube link
`second`	Yes	Seconds into the video: 1910 for 31:50

Output Schema

Name	Required	Description
`url`	Yes	The episode playing from that second
`cite`	Yes
`date`	Yes	When the episode came out, YYYY-MM-DD
`from`	Yes	Where the excerpt starts, like 31:40
`show`	Yes
`lines`	Yes
`moment`	No	The moment the second falls in, if any
`episode`	Yes
`transcript`	Yes	Where the transcript comes from

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 9, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": false,
+  "properties": {
+    "cite": {
+      "type": "string"
+    },
+    "date": {
+      "description": "When the episode came out, YYYY-MM-DD",
+      "type": "string"
+    },
+    "episode": {
+      "type": "string"
+    },
+    "from": {
+      "description": "Where the excerpt starts, like 31:40",
+      "type": "string"
+    },
+    "lines": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "at": {
+            "type": "string"
+          },
+          "speaker": {
+            "type": "string"
+          },
+          "text": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "at",
+          "text"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "moment": {
+      "additionalProperties": false,
+      "description": "The moment the second falls in, if any",
+      "properties": {
+        "title": {
+          "type": "string"
+        },
+        "url": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "title",
+        "url"
+      ],
+      "type": "object"
+    },
+    "show": {
+      "type": "string"
+    },
+    "transcript": {
+      "description": "Where the transcript comes from",
+      "type": "string"
+    },
+    "url": {
+      "description": "The episode playing from that second",
+      "type": "string"
+    }
+  },
+  "required": [
+    "episode",
+    "show",
+    "date",
+    "from",
+    "lines",
+    "transcript",
+    "url",
+    "cite"
+  ],
+  "type": "object"
+}

First observedOct 23, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, and the description adds real constraints on top: only episodes cut by Real Alpha have transcripts, never more than about a minute per call, and machine transcription can misspell names. It does not say what happens on a miss (error vs. empty result), which is the main remaining gap.

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?

Three sentences, front-loaded with what is returned and followed by the use case and caveats; nothing is filler. It is slightly roundabout in phrasing and repeats the 'Real Alpha cut' restriction in both the first and third sentences.

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 annotations covering the safety profile, a full input schema, and an output schema for return values, the description supplies the remaining operational facts: eligibility, excerpt size, and transcription reliability. An agent has enough to decide to call it and to interpret a degraded result.

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 baseline is 3, but the description adds meaning beyond the schema: `second` is the starting offset of the returned window and the window runs roughly sixty seconds, so the agent knows it is reading a slice, not the whole video. It also explains where to obtain `video` in practice (a moment's episode_url).

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

Purpose4/5

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

The opening states the resource concretely (about a minute of an episode's transcript starting at a given second) and enumerates what comes back: timed lines, speaker where known, and a deep link. It is distinguishable from summary-style siblings, but it never names an alternative tool and leads with a noun phrase rather than a verb, so the action is implied rather than declared.

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?

It gives a clear use case ('check the exact words around a moment's quote') and ties the parameters to a known source ('a moment's episode_url has the video id and second'). It also states hard availability limits. It stops short of telling the agent what to call instead when the need is a full transcript or a summary.

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

All Real Alpha 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.