Agent Tools API

Get YouTube video transcript

get_transcript

Read-onlyIdempotent

Fetch the full transcript of a YouTube video URL or ID as plain text, timestamped segments, SRT or VTT, optionally in a chosen or translated language. Use when the user asks to summarize, quote, search, or analyze a YouTube video, since the model cannot watch video. Takes one video per call. Returns one result with title, channel, language, whether captions are auto-generated, whether it fell back to another language, text and segments; a video without captions or one YouTube blocks comes back as status "error" with a code and retryable flag.

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>"
    },
    "name": "get_transcript"
  }
}

Input Schema

Name	Required	Description
`video`	Yes	YouTube video URL (watch, youtu.be, shorts, embed, live) or 11-character video ID
`format`	No	segments = timestamped JSON plus text (default), text = plain text only, srt/vtt = subtitle file
`languages`	No	Language codes in priority order, e.g. ["en", "pt-BR"]; a code also matches its regional variants. Defaults to ["en"]
`translateTo`	No	Translate the transcript into this language code when YouTube offers it
`fallbackToAnyLanguage`	No	When none of the languages exist, return the video's original-language transcript (languageFallback: true) instead of an error. Defaults to true

Output Schema

Name	Required	Description	Default
`cache`	Yes	How the result was served: HIT or STALE from a cache tier, MISS or BYPASS when it was fetched now.
`results`	Yes	One row for the video: the transcript, or an error with a code.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 10, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "cache": {
+      "description": "How the result was served: HIT or STALE from a cache tier, MISS or BYPASS when it was fetched now.",
+      "properties": {
+        "ageSeconds": {
+          "type": "number"
+        },
+        "source": {
+          "enum": [
+            "worker",
+            "origin",
+            "coalesced"
+          ],
+          "type": "string"
+        },
+        "status": {
+          "enum": [
+            "HIT",
+            "STALE",
+            "MISS",
+            "BYPASS"
+          ],
+          "type": "string"
+        },
+        "tier": {
+          "type": "string"
+        },
+        "ttlSeconds": {
+          "type": "number"
+        }
+      },
+      "required": [
+        "status",
+        "tier",
+        "ageSeconds",
+        "ttlSeconds"
+      ],
+      "type": "object"
+    },
+    "results": {
+      "description": "One row for the video: the transcript, or an error with a code.",
+      "items": {
+        "anyOf": [
+          {
+            "additionalProperties": true,
+            "properties": {
+              "channelName": {
+                "type": [
+                  "string",
+                  "null"
+                ]
+              },
+              "format": {
+                "enum": [
+                  "segments",
+                  "text",
+                  "srt",
+                  "vtt"
+                ],
+                "type": "string"
+              },
+              "isGenerated": {
+                "type": "boolean"
+              },
+              "language": {
+                "type": "string"
+              },
+              "languageCode": {
+                "type": "string"
+              },
+              "languageFallback": {
+                "type": "boolean"
+              },
+              "segmentCount": {
+                "type": "number"
+              },
+              "segments": {
+                "items": {
+                  "properties": {
+                    "duration": {
+                      "type": "number"
+                    },
+                    "start": {
+                      "type": "number"
+                    },
+                    "text": {
+                      "type": "string"
+                    }
+                  },
+                  "required": [
+                    "text",
+                    "start",
+                    "duration"
+                  ],
+                  "type": "object"
+                },
+                "type": "array"
+              },
+              "status": {
+                "const": "ok"
+              },
+              "subtitles": {
+                "type": "string"
+              },
+              "text": {
+                "type": "string"
+              },
+              "title": {
+                "type": [
+                  "string",
+                  "null"
+                ]
+              },
+              "translatedFrom": {
+                "type": [
+                  "string",
+                  "null"
+                ]
+              },
+              "videoId": {
+                "type": "string"
+              }
+            },
+            "required": [
+              "status",
+              "videoId",
+              "languageCode",
+              "isGenerated",
+              "languageFallback",
+              "format",
+              "text",
+              "segmentCount"
+            ],
+            "type": "object"
+          },
+          {
+            "additionalProperties": true,
+            "properties": {
+              "error": {
+                "additionalProperties": true,
+                "properties": {
+                  "code": {
+                    "type": "string"
+                  },
+                  "message": {
+                    "type": "string"
+                  },
+                  "retryable": {
+                    "type": "boolean"
+                  }
+                },
+                "required": [
+                  "code",
+                  "message",
+                  "retryable"
+                ],
+                "type": "object"
+              },
+              "status": {
+                "const": "error"
+              },
+              "videoId": {
+                "type": [
+                  "string",
+                  "null"
+                ]
+              }
+            },
+            "required": [
+              "status",
+              "error"
+            ],
+            "type": "object"
+          }
+        ]
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "results",
+    "cache"
+  ],
+  "type": "object"
+}

First observedOct 3, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already carry the safety profile (readOnly, idempotent, openWorld, non-destructive), and the description adds real behavior beyond them: one video per call, the returned fields (title, channel, language, auto-generated flag, languageFallback), and the failure mode where a video without captions or a blocked video returns status "error" with a code and retryable flag. It does not mention auth or quota/rate-limit behavior, so a 4 rather than a 5.

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?

Two dense sentences that front-load the verb and resource, then usage triggers, then return/failure shape. Nothing is wasted, though the second sentence packs return fields that the output schema already supplies.

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, the description does not need to enumerate return values, yet it usefully flags the error path and its retryable flag. Coverage of the tool's behavior for its five parameters is adequate; only auth/quota expectations are unaddressed.

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 the schema already documents format values, language-code priority, translateTo, and the fallbackToAnyLanguage default. The description's parameter framing ("chosen or translated language") largely restates this, so the baseline 3 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?

States a specific verb (fetch) plus resource (full transcript of a YouTube video URL or ID) and enumerates the output shapes (plain text, timestamped segments, SRT, VTT) and language options. An agent can distinguish this from every sibling, none of which touch video transcripts.

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 explicit triggers (summarize, quote, search, analyze a YouTube video) and the rationale that the model cannot watch video, which is exactly the condition that selects this tool. It also bounds the call ("Takes one video per call"), but offers no when-not-to-use guidance, so it falls short of a 5.

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

All Agent Tools API 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.