StudioSphere Pulse — Audio Intelligence

analyze_track

Run audio analysis on a public audio URL. Requires estimate_cost to be called first (job_estimate_id). Requires PULSE_API_KEY. Before calling, you MUST confirm with the user that they have a lawful basis to submit this audio for analysis. For a user-requested folder, project, playlist, or batch, one confirmation can cover every track in that scope. Returns job_id — poll get_job_status for results.

Input Schema

TableJSON Schema

Name	Required	Description
`tools`	Yes	Analysis tools to run. Available in v1.0: bpm, key, waveform. Coming soon: structure, chords.
`audio_url`	Yes	Public URL of the audio file.
`job_estimate_id`	Yes	The job_estimate_id returned by estimate_cost. Must not be expired (30 min TTL).
`attestation_confirmed`	Yes	Set to true ONLY after the user has confirmed they have rights, permission, lawful access, or another legal basis to submit this audio, or the current user-requested batch/folder/project containing it, for analysis.

Output Schema

TableJSON Schema

Name	Required	Description
`ok`	No	True when analysis was accepted.
`error`	No	Machine-readable error code.
`job_id`	No	Pulse analysis job id.
`status`	No	Current job status.
`details`	No	Additional structured context from Pulse.
`message`	No	Human-readable recovery guidance.
`poll_url`	No	Relative status polling URL.
`retryable`	No	Whether the caller may retry after changing state or waiting.
`cache_hits`	No	Tools served from cache.
`stream_url`	No	Relative SSE status URL.
`account_type`	No	Account type used for the request.
`upgrade_path`	No
`conversion_note`	No
`tokens_estimated`	No	Estimated token charge.
`cost_usd_estimated`	No	Estimated USD value.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedJun 19, 2026

addedOutput schema / anyOf

Added value: +[
+  {
+    "required": [
+      "ok",
+      "job_id",
+      "status",
+      "cache_hits",
+      "tokens_estimated",
+      "cost_usd_estimated",
+      "poll_url",
+      "stream_url"
+    ]
+  },
+  {
+    "required": [
+      "error",
+      "message"
+    ]
+  }
+]

addedOutput schema / properties

Added value: +{
+  "account_type": {
+    "description": "Account type used for the request.",
+    "type": "string"
+  },
+  "cache_hits": {
+    "description": "Tools served from cache.",
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  },
+  "conversion_note": {
+    "type": "string"
+  },
+  "cost_usd_estimated": {
+    "description": "Estimated USD value.",
+    "type": "number"
+  },
+  "details": {
+    "additionalProperties": true,
+    "description": "Additional structured context from Pulse.",
+    "type": "object"
+  },
+  "error": {
+    "description": "Machine-readable error code.",
+    "type": "string"
+  },
+  "job_id": {
+    "description": "Pulse analysis job id.",
+    "type": "string"
+  },
+  "message": {
+    "description": "Human-readable recovery guidance.",
+    "type": "string"
+  },
+  "ok": {
+    "description": "True when analysis was accepted.",
+    "type": "boolean"
+  },
+  "poll_url": {
+    "description": "Relative status polling URL.",
+    "type": "string"
+  },
+  "retryable": {
+    "description": "Whether the caller may retry after changing state or waiting.",
+    "type": "boolean"
+  },
+  "status": {
+    "description": "Current job status.",
+    "type": "string"
+  },
+  "stream_url": {
+    "description": "Relative SSE status URL.",
+    "type": "string"
+  },
+  "tokens_estimated": {
+    "description": "Estimated token charge.",
+    "type": "number"
+  },
+  "upgrade_path": {
+    "type": "string"
+  }
+}

addedOutput schema / required
```
Added value: +[]
```

Changed1 schema field changedMay 2, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "type": "object"
+}

Changed1 schema field changedMay 2, 2026

changedInput schema / properties / attestation_confirmed / description

Previous value: -"Set to true ONLY after the user has confirmed they have rights, permission, lawful access, or another legal basis to submit this audio for analysis."New value: +"Set to true ONLY after the user has confirmed they have rights, permission, lawful access, or another legal basis to submit this audio, or the current user-requested batch/folder/project containing it, for analysis."

Changed1 schema field changedMay 1, 2026

changedInput schema / properties / attestation_confirmed / description

Previous value: -"Set to true ONLY after the user has confirmed they have the right to submit this audio."New value: +"Set to true ONLY after the user has confirmed they have rights, permission, lawful access, or another legal basis to submit this audio for analysis."

First observedMay 1, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Beyond the annotations (readOnlyHint=false, idempotentHint=false), the description adds significant behavioral context: requires PULSE_API_KEY, requires prior estimate, must confirm lawful basis, and returns a job_id for async polling. It also clarifies that one batch confirmation covers multiple tracks, which is critical for proper use. No contradiction with annotations.

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?

Five sentences, each carrying essential information: main action, prerequisite, API key requirement, user confirmation obligation, and return/poll behavior. No fluff or redundancy.

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 tool with an output schema (returns job_id) and this complexity, the description covers the full workflow: prerequisites, legal compliance, return behavior, and the async polling pattern. It does not need to explain return values in detail because the output schema exists.

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. The description adds meaning by explaining the workflow dependency (job_estimate_id comes from estimate_cost), reinforces the 'public' nature of audio_url, and clarifies the legal confirmation requirement for attestation_confirmed. This goes beyond the schema's per-parameter descriptions.

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?

The description opens with a clear verb+resource: 'Run audio analysis on a public audio URL.' It distinguishes itself from siblings by explicitly linking to estimate_cost (prerequisite) and get_job_status (result retrieval), making it unambiguous which step in the workflow this tool represents.

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?

The description clearly states the prerequisite (estimate_cost must be called first) and the follow-up (poll get_job_status). It also provides guidance on batch confirmation. However, it does not explicitly state when not to use this tool (e.g., for cost estimation or status polling), though the workflow context makes this implicitly clear.

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

All StudioSphere Pulse — Audio Intelligence 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.