Nopaque TotalPath

List Audio Files

listAudio

Read-onlyIdempotent

List the audio library in your workspace: recordings, uploads and generated speech, each with an id, category, filename, content type, size, duration, when it was created and the id of what it belongs to (associatedId, e.g. a run). Takes optional filters: category or categories (comma-separated), associatedId (all audio for one run or job), search (part of the name, any case), dateFrom / dateTo, sourceType (recorded, uploaded or generated), sortDirection (asc or desc), limit and cursor. Use when: the user asks what recordings or uploaded prompts they have, or whether a run has audio. Returns metadata only, never the audio or a link to it: the person plays or downloads it in the web app. Read-only. Needs audio:read.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "listAudio"
  }
}

Input Schema

Name	Required	Description	Default
`limit`	No	Max items to return.
`cursor`	No	Opaque pagination cursor from a previous response's `nextCursor`.
`dateTo`	No	ISO 8601 upper bound (inclusive) on `createdAt`.
`search`	No	Case-insensitive substring match against filename, computed display name, and description — searched server-side across the full paginated history, not just the current page.
`category`	No	Bucket used by the upload-URL handler to derive the S3 key. Audio files for test runs live under `tests/`, mapping recordings under `maps/`, voice profiles under `voices/`, and transcript audio under `transcripts/`.
`dateFrom`	No	ISO 8601 lower bound (inclusive) on `createdAt`.
`categories`	No	Comma-separated list of categories (e.g. `voice,test,map`). Presence of this param (or `search`/`dateFrom`/`dateTo`/`sourceType`/`cursor`) activates the cursor-paginated full-history query path.
`sourceType`	No	Voice-only sub-filter on `metadata.source`. Only meaningful paired with `categories=voice`. `generated` is speech made with `POST /audio/generate`; `uploaded` is everything that is neither recorded nor generated.
`associatedId`	No	Filter to audio owned by a specific parent entity (e.g. a `runId`). Note this query uses a cross-workspace GSI; callers should only pass ids they obtained from other workspace-scoped responses. Mutually exclusive with the categories/search/date-range/cursor path.
`sortDirection`	No	Native `createdAt` order. Default matches pre-fix behaviour (newest-first).	desc

Output Schema

Name	Required	Description
`count`	Yes	Number of items in the page.
`audioFiles`	Yes
`nextCursor`	No	Present when more history is available. Pass back as `cursor` to fetch the next page. Only populated when the `categories`/`search`/`dateFrom`/`dateTo`/ `sourceType`/`cursor` pagination path is used.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 11, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Beyond the annotations (readOnly, idempotent, non-destructive), it discloses that only metadata is returned and never the audio or a link, that the audio:read scope is required, and that associatedId uses a cross-workspace index and is mutually exclusive with the cursor-paginated filter path. Those are non-obvious constraints an agent could not infer from structured fields.

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?

Content is front-loaded with purpose, then filters, then when-to-use, then the return/auth caveat, so an agent can stop reading early. The filter enumeration is somewhat list-like and duplicates schema terms, but each sentence carries actionable 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 10-parameter filtered list tool with a full output schema, the description covers scope, filter interplay, authorization, and the metadata-only return boundary. An agent has everything needed to decide to call it and to pick a filter path without opening the schema.

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 coverage is 100% and the schema already explains category buckets, sourceType enums, the comma-separated categories form, and the cursor path activation. The description mostly restates these in prose, adding only light framing such as "all audio for one run or job" for associatedId, so the baseline of 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?

The description opens with a specific verb and resource ("List the audio library in your workspace") and enumerates the three content kinds returned (recordings, uploads, generated speech) plus the metadata fields. This clearly separates it from the singular getAudio sibling without needing to name it.

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 an explicit "Use when" clause covering the two common intents (inventory of recordings/uploads, or checking whether a run has audio), and it warns that the audio itself must be fetched in the web app. It stops short of naming the sibling tool that fetches a single item, so routing is implied rather than fully closed.

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

All Nopaque TotalPath 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.