karaoke-maker-3000

Get karaoke

get_karaoke

Read-only

Read a Quick project's authoritative status, progress, allowed actions and current MP4 links. While processing, this read waits up to 20 seconds for completion or an actionable state and returns the newest status. After a start or a request to monitor, keep calling this tool for the same project in the current turn until ready, failure, cancellation or lyrics review; do not ask the user to request each check. Do not repeat start or automatically retry a failure. Always use the project_id returned by an upload ticket to reconcile a timeout or lost raw-upload response before declaring failure or creating another upload. An existing awaiting_start draft means the audio arrived: resume its current quote. For that issued ID only, an immediate not_found during an in-flight upload is inconclusive; briefly wait and recheck the same ID once, then report receipt as unconfirmed if it is still unavailable. Do not infer that the server is down from a timeout alone. Discuss quotes, processing, errors and corrections in the conversation. Only after this reports a current ready MP4 and no lyrics review, call show_karaoke to display the finished preview and download.

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": {
      "project_id": "<project_id>"
    },
    "name": "get_karaoke"
  }
}

Input Schema

Name	Required	Description	Default
`project_id`	Yes

Output Schema

Name	Required	Description	Default
`error`	No
`media`	No
`quote`	No
`stage`	No
`status`	No
`visual`	No
`project`	No
`progress`	No
`can_retry`	No
`can_start`	No
`demo_mode`	No
`can_cancel`	No
`project_id`	No
`studio_url`	No
`can_handoff`	No
`lyrics_source`	No
`preview_ready`	No
`visual_source`	No
`visual_warning`	No
`command_version`	No
`project_revision`	No
`can_replace_lyrics`	No
`can_update_visuals`	No
`visual_preferences`	No
`needs_lyrics_review`	No
`lyrics_search_outcome`	No
`lyrics_search_provider`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedNov 13, 2026

changedOutput schema / oneOf

Previous value: -[
-  {
-    "required": [
-      "project_id",
-      "project_revision",
-      "command_version",
-      "status",
-      "stage",
-      "quote",
-      "can_start",
-      "can_retry",
-      "can_cancel",
-      "can_handoff",
-      "preview_ready",
-      "needs_lyrics_review",
-      "progress",
-      "visual_preferences",
-      "visual",
-      "visual_source",
-      "visual_warning",
-      "error",
-      "lyrics_source",
-      "lyrics_search_outcome",
-      "lyrics_search_provider",
-      "demo_mode",
-      "project",
-      "studio_url",
-      "media"
-    ]
-  },
-  {
-    "maxProperties": 1,
-    "properties": {
-      "error": {
-        "additionalProperties": true,
-        "maxProperties": 32,
-        "properties": {
-          "code": {
-            "maxLength": 120,
-            "minLength": 1,
-            "type": "string"
-          },
-          "message": {
-            "maxLength": 2000,
-            "minLength": 1,
-            "type": "string"
-          },
-          "retryable": {
-            "type": "boolean"
-          }
-        },
-        "required": [
-          "code",
-          "message",
-          "retryable"
-        ],
-        "type": "object"
-      }
-    },
-    "required": [
-      "error"
-    ]
-  }
-]New value: +[
+  {
+    "required": [
+      "project_id",
+      "project_revision",
+      "command_version",
+      "status",
+      "stage",
+      "quote",
+      "can_start",
+      "can_retry",
+      "can_cancel",
+      "can_handoff",
+      "preview_ready",
+      "needs_lyrics_review",
+      "can_replace_lyrics",
+      "can_update_visuals",
+      "progress",
+      "visual_preferences",
+      "visual",
+      "visual_source",
+      "visual_warning",
+      "error",
+      "lyrics_source",
+      "lyrics_search_outcome",
+      "lyrics_search_provider",
+      "demo_mode",
+      "project",
+      "studio_url",
+      "media"
+    ]
+  },
+  {
+    "maxProperties": 1,
+    "properties": {
+      "error": {
+        "additionalProperties": true,
+        "maxProperties": 32,
+        "properties": {
+          "code": {
+            "maxLength": 120,
+            "minLength": 1,
+            "type": "string"
+          },
+          "message": {
+            "maxLength": 2000,
+            "minLength": 1,
+            "type": "string"
+          },
+          "retryable": {
+            "type": "boolean"
+          }
+        },
+        "required": [
+          "code",
+          "message",
+          "retryable"
+        ],
+        "type": "object"
+      }
+    },
+    "required": [
+      "error"
+    ]
+  }
+]

addedOutput schema / properties / can_replace_lyrics
```
Added value: +{
+  "type": "boolean"
+}
```
addedOutput schema / properties / can_update_visuals
```
Added value: +{
+  "type": "boolean"
+}
```

addedOutput schema / properties / project / properties / has_lyrics

Added value: +{
+  "type": [
+    "boolean",
+    "null"
+  ]
+}

changedOutput schema / properties / project / required

Previous value: -[
-  "id",
-  "title",
-  "artist",
-  "duration_seconds",
-  "revision",
-  "has_export",
-  "export_status",
-  "visual_settings"
-]New value: +[
+  "id",
+  "title",
+  "artist",
+  "duration_seconds",
+  "revision",
+  "has_export",
+  "has_lyrics",
+  "export_status",
+  "visual_settings"
+]

First observedNov 12, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations declare a safe read, but the description adds substantial behavior beyond them: a blocking wait of up to 20 seconds, newest-status return semantics, in-flight-upload not_found being inconclusive with one brief recheck, and the rule not to infer server downtime from a timeout alone. These are exactly the operational traits an agent needs and cannot get from readOnlyHint or idempotentHint (the latter is declared false, consistent with status changing between calls).

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 what is returned and the 20-second wait, followed by ordered operational rules. It is dense and every sentence carries a rule, though a few clauses (upload reconciliation, not_found handling, quote resumption) make it long enough that an agent must read carefully rather than skim.

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?

For an asynchronous polling tool with an output schema, the definition covers the full lifecycle an agent must handle: timeout reconciliation, in-flight upload ambiguity, awaiting_start drafts, failure and lyrics-review stop conditions, and the handoff to show_karaoke. Nothing material for correct invocation is missing.

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?

The single parameter has zero schema description coverage, so the description must carry the meaning. It does add important provenance and handling semantics: the project_id must come from an upload ticket, and reconciliation rules apply specifically to that issued ID. It does not restate the pattern or length constraints, but those are in the schema, so this is close to complete.

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?

Names a specific verb and resource ('Read a Quick project's authoritative status, progress, allowed actions and current MP4 links') and explicitly separates itself from show_karaoke, which is only for display after readiness. An agent can distinguish it from get_karaoke_lyrics, list_karaokes and the start/retry mutations without opening another 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?

Extremely explicit: keep polling in the current turn until ready, failure, cancellation or lyrics review; never ask the user to trigger each check; never repeat start or auto-retry a failure; use the upload-ticket project_id to reconcile timeouts; treat an awaiting_start draft as audio received and resume its quote; only call show_karaoke after a current ready MP4 with no lyrics review. Both when-to-use and when-not-to-use are stated, along with the sibling alternative.

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

All karaoke-maker-3000 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?