Skip to main content
Glama

calls_dispatch_translator

Read-onlyIdempotent

Send a live speech translator to a call. target decides where: a Google Meet, Microsoft Teams or Zoom link → meeting bot; a Telegram @group / t.me link / chat_id → Telegram group voice chat; 'new' (or omitted) → creates a native DialogBrain meeting with translation on and returns the join + guest links; a native meeting call_id or /meeting/ URL → enables translation on that running meeting. Always pass target_language (ISO code); optional app_languages (extra subtitle-only languages), sentence_length (short|medium|long, native only), silent (subtitles without voice), source_language (the meeting's spoken language, ISO code — improves recognition; omit for autodetect), tts_provider + tts_voice (the translator's voice; omit for the workspace default).

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": {
      "target_language": "<target_language>"
    },
    "name": "calls_dispatch_translator"
  }
}

Input Schema

NameRequiredDescriptionDefault
titleNonative_new only: meeting title.
silentNoMeeting routes only (Google Meet / Teams / Zoom): true = subtitles without speaking into the call. OMIT for a normal speaking translator.
targetNoWhere to send the translator: a Google Meet, Microsoft Teams or Zoom link, a Telegram @group / t.me link / chat_id, 'new' for a fresh native meeting, or an existing native meeting call_id or /meeting/ URL. Omit for a new native meeting.
agent_idNoMeeting routes ONLY (Google Meet / Teams / Zoom), and required there: the active agent the bot session is recorded against (calls.send_to_meet needs one). Get it from agents.list. Telegram and native meetings ignore it — they arm translation on a call that already exists.
tts_voiceNoSpecific voice id for tts_provider (e.g. 'alena', 'nova'). Omit for the provider default.
in_workspaceNoRun this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected.
tts_providerNoTranslator VOICE provider (cartesia, openai, deepgram, ...). Omit for the workspace default translation voice. Meeting routes (Google Meet / Teams / Zoom) + native new meetings.
app_languagesNoExtra subtitle-only languages (max 4).
comeback_phraseNoAttention-recall phrase.
sentence_lengthNoNative meetings only: short|medium|long buffering (default medium).
source_languageNoThe call's spoken language (ISO code, e.g. 'en', 'ru'). When set, speech recognition runs in that language's dedicated mode for better accuracy. REQUIRED in practice for languages autodetect does not cover (e.g. 'vi', 'th', 'id', 'tl'). Omit when participants may speak multiple languages (autodetect). All routes.
target_languageYesPrimary spoken translation target (ISO code, e.g. 'th').
channel_account_idNoTelegram group route: the workspace Telegram account that joins the call (id from channels.list). Optional with exactly one Telegram account; required with several.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / agent_id / description
      Previous value: -"Meeting routes ONLY (Google Meet / Teams), and required there: the active agent the bot session is recorded against (calls.send_to_meet needs one). Get it from agents.list. Telegram and native meetings ignore it — they arm translation on a call that already exists."New value: +"Meeting routes ONLY (Google Meet / Teams / Zoom), and required there: the active agent the bot session is recorded against (calls.send_to_meet needs one). Get it from agents.list. Telegram and native meetings ignore it — they arm translation on a call that already exists."
    • changedInput schema / properties / silent / description
      Previous value: -"Meeting routes only (Google Meet / Teams): true = subtitles without speaking into the call. OMIT for a normal speaking translator."New value: +"Meeting routes only (Google Meet / Teams / Zoom): true = subtitles without speaking into the call. OMIT for a normal speaking translator."
    • changedInput schema / properties / tts_provider / description
      Previous value: -"Translator VOICE provider (cartesia, openai, deepgram, ...). Omit for the workspace default translation voice. Meeting routes (Google Meet / Teams) + native new meetings."New value: +"Translator VOICE provider (cartesia, openai, deepgram, ...). Omit for the workspace default translation voice. Meeting routes (Google Meet / Teams / Zoom) + native new meetings."
  2. Changed1 schema field changed
    • changedInput schema / properties / target / description
      Previous value: -"Where to send the translator: a Google Meet or Microsoft Teams link, a Telegram @group / t.me link / chat_id, 'new' for a fresh native meeting, or an existing native meeting call_id or /meeting/ URL. Omit for a new native meeting."New value: +"Where to send the translator: a Google Meet, Microsoft Teams or Zoom link, a Telegram @group / t.me link / chat_id, 'new' for a fresh native meeting, or an existing native meeting call_id or /meeting/ URL. Omit for a new native meeting."
  3. Changed1 schema field changed
    • addedInput schema / properties / channel_account_id
      Added value: +{
      +  "description": "Telegram group route: the workspace Telegram account that joins the call (id from channels.list). Optional with exactly one Telegram account; required with several.",
      +  "type": "integer"
      +}
  4. Changed1 schema field changed
    • changedInput schema / properties / tts_provider / description
      Previous value: -"Translator VOICE provider (cartesia, openai, yandex, deepgram, ...). Omit for the workspace default translation voice. Meeting routes (Google Meet / Teams) + native new meetings."New value: +"Translator VOICE provider (cartesia, openai, deepgram, ...). Omit for the workspace default translation voice. Meeting routes (Google Meet / Teams) + native new meetings."
  5. Changed1 schema field changed
    • addedInput schema / properties / in_workspace
      Added value: +{
      +  "description": "Run this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected.",
      +  "type": "integer"
      +}
  6. Added
  7. Removed
  8. Changed3 schema fields changed
    • addedInput schema / properties / source_language
      Added value: +{
      +  "description": "The meeting's spoken language (ISO code, e.g. 'en', 'ru'). When set, speech recognition runs in that language's dedicated mode for better accuracy. Omit when participants may speak multiple languages (autodetect). Google Meet + native meetings.",
      +  "type": "string"
      +}
    • addedInput schema / properties / tts_provider
      Added value: +{
      +  "description": "Translator VOICE provider (cartesia, openai, yandex, deepgram, ...). Omit for the workspace default translation voice. Google Meet + native new meetings.",
      +  "type": "string"
      +}
    • addedInput schema / properties / tts_voice
      Added value: +{
      +  "description": "Specific voice id for tts_provider (e.g. 'alena', 'nova'). Omit for the provider default.",
      +  "type": "string"
      +}
  9. Added

TDQS

A3.9/5.0
Behavior2/5

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

Annotations declare readOnlyHint=true and idempotentHint=true, yet the description says the tool sends bots into live third-party calls and, with 'new' or omitted target, 'creates a native DialogBrain meeting' — a state-changing, non-idempotent action. The text does add real behavioral context absent from annotations (agent_id required on meeting routes, channel_account_id conditional on one vs. several Telegram accounts, source_language needed for languages autodetect misses), but the core conflict with the safety annotations remains.

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-loads the routing decision in a single sentence, then lists options in one dense clause; nearly every phrase carries information. It is long but justified by 13 parameters and four distinct routing branches, with only minor repetition of schema-documented defaults.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 13-parameter, multi-surface dispatch tool with no output schema, the description covers routing, required vs. optional options, and return behavior for the 'new' branch (join + guest links). It is silent on what a successful meeting-bot or Telegram dispatch returns and on any permission or cost implications, which an agent would need to reason about.

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 the baseline is 3; the description still adds genuine cross-parameter meaning by stating which routes each option applies to (sentence_length native-only, silent meeting-routes-only, app_languages subtitle-only, tts_provider/tts_voice defaults). This route-gating logic is not derivable from the flat schema alone.

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 and resource ('Send a live speech translator to a call') and immediately enumerates what `target` means for every surface: Meet/Teams/Zoom link, Telegram group, 'new', or an existing native meeting. An agent can tell exactly what this does and how it differs from the mute/set-language siblings without opening the schema.

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 clear per-branch routing rules including the default case ('new' or omitted creates a native meeting) and the follow-on action for an existing call_id/URL. It lacks explicit when-not-to-use guidance or named alternatives (e.g. calls_set_translation_language, calls_mute_translation_tts), so an agent must infer that this is the dispatch step rather than the in-call adjustment step.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.