Skip to main content
Glama

Play audio to a conference member

play_audio_to_conference_member
Destructive

Play an audio file privately to selected Vobiz conference members for whispered prompts or announcements. Target individuals or all members; stop playback early if needed.

Instructions

Play an audio file (https .mp3/.wav) privately to members of a live Vobiz conference (POST /Conference/{name}/Member/{id}/Play/); other members do not hear it. Use it for whispered prompts or announcements, or pass member_id all to reach the whole room. Vobiz accepts the request (202) and starts playback asynchronously; stop it early with stop_audio_to_conference_member. A room that is not running, or a member who already left, returns the not_found error.

Input Schema

NameRequiredDescriptionDefault
urlYesPublic https URL of the .mp3 or .wav file to play; its host must be approved by the server.
member_idYesConferenceMemberID from the ConferenceEnter callback (or get_conference), a comma-separated list such as 17,45,82, or `all` for every member.
conference_nameYesConference room name, exactly as used in the <Conference> XML element.

Output Schema

NameRequiredDescriptionDefault
okNoTrue on success; false when the result is an error (then error, message and retryable are set).
playingNoAlways true: playback was accepted.
member_idNoMembers the action was applied to: the literal "all", or the list of member IDs as Vobiz echoed them (or as requested).
http_statusNoHTTP status Vobiz answered with (202 = accepted, 204 = done).
backend_messageNoVobiz's own status message, or null.
conference_nameNoRoom the action was applied to.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.4.2
    • changedInput schema / properties / url / description
      Previous value: -"Audio file to play (https .mp3 or .wav)."New value: +"Public https URL of the .mp3 or .wav file to play; its host must be approved by the server."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "$schema": "http://json-schema.org/draft-07/schema#",
      +  "additionalProperties": {},
      +  "properties": {
      +    "backend_message": {
      +      "description": "Vobiz's own status message, or null."
      +    },
      +    "conference_name": {
      +      "description": "Room the action was applied to.",
      +      "type": "string"
      +    },
      +    "http_status": {
      +      "description": "HTTP status Vobiz answered with (202 = accepted, 204 = done).",
      +      "type": "number"
      +    },
      +    "member_id": {
      +      "anyOf": [
      +        {
      +          "type": "string"
      +        },
      +        {
      +          "items": {},
      +          "type": "array"
      +        }
      +      ],
      +      "description": "Members the action was applied to: the literal \"all\", or the list of member IDs as Vobiz echoed them (or as requested)."
      +    },
      +    "ok": {
      +      "description": "True on success; false when the result is an error (then error, message and retryable are set).",
      +      "type": "boolean"
      +    },
      +    "playing": {
      +      "const": true,
      +      "description": "Always true: playback was accepted.",
      +      "type": "boolean"
      +    }
      +  },
      +  "type": "object"
      +}
  2. First observedv1.1.1

TDQS

A4.5/5.0
Behavior5/5

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

Adds substantial behavior beyond the annotations: async 202 acceptance, immediate start of playback, the early-stop sibling, and the not_found failure mode for a stopped room or departed member. The destructiveHint=true annotation is consistent with an operation that injects audio into a live call.

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?

Three dense sentences: purpose and privacy constraint first, then usage and the all-member case, then async/error behavior. No filler, and the most important selection cue (private playback) is front-loaded.

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 3-param action tool with full schema coverage, an output schema, and safety annotations, the description covers everything an agent needs: what it does, the audience scope, async semantics, and failure conditions.

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%, so url, member_id (including the 'all' and comma-list semantics), and conference_name are already fully documented in the schema. The description reinforces but does not add meaning beyond it, so 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+resource+scope: play an audio file privately to members of a live Vobiz conference, with the endpoint spelled out. It clearly distinguishes itself from sibling tools like play_audio and speak_text by emphasizing private, conference-member-scoped playback.

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 concrete usage context (whispered prompts, announcements) and explains the member_id=all case for reaching the whole room, plus names stop_audio_to_conference_member for early termination. It does not explicitly contrast with the non-conference play_audio sibling, so it falls just short of full when/when-not guidance.

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

Deploy Server

Other Tools