Magic Hour

Wait for Audio Project

wait_for_audio_project

Read-onlyIdempotent

Polls an audio project until it completes, errors, is canceled or times out. Use with the id returned by an audio create tool. Read-only; returns the project and download URLs, with optional inline audio previews sharing an 8 MiB total limit. After a timeout, resume with the same id rather than creating another generation. Use signed download URLs exactly as returned.

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": {
      "id": "<id>"
    },
    "name": "wait_for_audio_project"
  }
}

Input Schema

Name	Required	Description
`id`	Yes	Existing project ID returned by the matching creation tool. Reuse this ID after a wait timeout.
`timeout_seconds`	No	Maximum seconds for this wait call, finite and greater than zero. Timeout does not cancel the project or start another generation.
`max_inline_downloads`	No	Maximum number of previews to include. Zero or negative disables previews; previews share an 8 MiB total limit.
`poll_interval_seconds`	No	Seconds between status checks. Must be finite and nonnegative; values below 0.5 use 0.5 seconds.
`max_bytes_per_download`	No	Positive maximum raw bytes per preview, capped by the remaining 8 MiB total budget. Larger outputs remain available by URL.
`include_inline_downloads`	No	Whether to include image or audio previews for completed projects. Download URLs remain available if preview fetching fails.

Output Schema

Name	Required	Description
`id`	No	Existing project identifier, retained for subsequent status checks.
`status`	No	Project status such as complete, error or canceled; timeout means only this wait call ended.
`message`	No	Wait timeout or recovery guidance, when present.
`downloads`	No	Available output files with exact signed URLs. May be absent until completion.
`last_project`	No	Last observed API project snapshot if the wait timed out after a successful status check.
`project_type`	Yes	Kind of project being retrieved.
`exact_download_urls`	No	Convenience list of the same unmodified signed output URLs.
`download_expiration_metadata`	No	Expiration metadata only. Never append it to a download URL.

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedNov 12, 2026

addedInput schema / properties / id / description

Added value: +"Existing project ID returned by the matching creation tool. Reuse this ID after a wait timeout."

addedInput schema / properties / include_inline_downloads / description

Added value: +"Whether to include image or audio previews for completed projects. Download URLs remain available if preview fetching fails."

addedInput schema / properties / max_bytes_per_download / description

Added value: +"Positive maximum raw bytes per preview, capped by the remaining 8 MiB total budget. Larger outputs remain available by URL."

addedInput schema / properties / max_inline_downloads / description

Added value: +"Maximum number of previews to include. Zero or negative disables previews; previews share an 8 MiB total limit."

addedInput schema / properties / poll_interval_seconds / description

Added value: +"Seconds between status checks. Must be finite and nonnegative; values below 0.5 use 0.5 seconds."

addedInput schema / properties / timeout_seconds / description

Added value: +"Maximum seconds for this wait call, finite and greater than zero. Timeout does not cancel the project or start another generation."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "description": "Existing project status and exact output links. A wait timeout is not a generation failure; resume with the same ID.",
+  "properties": {
+    "download_expiration_metadata": {
+      "description": "Expiration metadata only. Never append it to a download URL.",
+      "items": {
+        "properties": {
+          "download_index": {
+            "description": "Zero-based index in the upstream download list, encoded as text.",
+            "type": "string"
+          },
+          "expires_at": {
+            "description": "Expiration timestamp provided by the API.",
+            "type": "string"
+          },
+          "note": {
+            "description": "Guidance for preserving the signed URL.",
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "downloads": {
+      "description": "Available output files with exact signed URLs. May be absent until completion.",
+      "items": {
+        "properties": {
+          "url": {
+            "description": "Use this signed download URL unchanged, including all query parameters.",
+            "type": "string"
+          }
+        },
+        "required": [
+          "url"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "exact_download_urls": {
+      "description": "Convenience list of the same unmodified signed output URLs.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "id": {
+      "description": "Existing project identifier, retained for subsequent status checks.",
+      "type": "string"
+    },
+    "last_project": {
+      "description": "Last observed API project snapshot if the wait timed out after a successful status check.",
+      "type": "object"
+    },
+    "message": {
+      "description": "Wait timeout or recovery guidance, when present.",
+      "type": "string"
+    },
+    "project_type": {
+      "description": "Kind of project being retrieved.",
+      "enum": [
+        "image",
+        "video",
+        "audio"
+      ],
+      "type": "string"
+    },
+    "status": {
+      "description": "Project status such as complete, error or canceled; timeout means only this wait call ended.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "project_type"
+  ],
+  "type": "object"
+}

Changed1 schema field changedOct 17, 2026
- changedInput schema / properties / max_bytes_per_download / default
```
Previous value: -15728640New value: +8388608
```

Changed1 schema field changedSep 24, 2026

removedInput schema / properties / context

Removed value: -{
-  "description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\"",
-  "type": "string"
-}

Changed1 schema field changedSep 11, 2026

addedInput schema / properties / context

Added value: +{
+  "description": "Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\"",
+  "type": "string"
+}

First observedSep 1, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses timeout semantics (does not cancel the project), the 8 MiB shared preview budget, signed-URL handling, and that previews are optional. That is real behavioral context the annotations don't carry, only the pagination/response-shape detail is thinner.

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?

Four short sentences, front-loaded with the polling semantics, then the id contract, the return and size limits, and the timeout recovery rule. Every sentence 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?

For a 6-parameter polling tool with full schema coverage, an output schema, and rich annotations, the description covers the remaining gaps: timeout behavior, id reuse, preview budget, and download URL usage. Nothing an agent needs to call it correctly is absent.

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 baseline is 3. The description reinforces two parameter behaviors—id reuse after timeout and inline-preview size limits—but adds no syntax or format detail the schema doesn't already state.

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 description states a specific verb and resource plus terminal conditions: 'Polls an audio project until it completes, errors, is canceled or times out.' That distinguishes polling from a one-shot fetch, though it never names get_audio_project as the alternative, so an agent must infer the split.

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 clear usage context ('Use with the id returned by an audio create tool') and an explicit don't-do-this rule ('After a timeout, resume with the same id rather than creating another generation'). What's missing is guidance on when a one-shot status check beats polling.

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

All Magic Hour 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?