Skip to main content
Glama

calls_dispatch_agent

Read-onlyIdempotent

Send a workspace AI agent into a live call — ONE tool for every surface; target decides where: a Google Meet, Microsoft Teams or Zoom link → meeting bot; a Telegram @group / t.me link / chat_id / t.me/call slug → Telegram group voice chat or conference; 'new' → creates a NEW Telegram conference call and returns its shareable link; a WhatsApp group JID (digits@g.us) → WhatsApp group call; a live session UUID (from calls.list_active), or thread_id of a running call → WAKES the agent on the bot already in that call instead of spawning a second one. For a meeting link the router also checks for a bot already in that meeting and wakes it rather than double-joining. Always pass agent_id (from agents.list). For a live TRANSLATOR use calls.dispatch_translator instead. agent_id must be an ACTIVE agent of this workspace — a system template is refused (create an agent from it first with agents.create). To take the agent off the call again while the bot keeps transcribing, use calls.dismiss_agent.

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": {
      "agent_id": "<agent_id>"
    },
    "name": "calls_dispatch_agent"
  }
}

Input Schema

NameRequiredDescriptionDefault
titleNotarget='new' only: label for the new conference.
targetNoWhere to send the agent: a Google Meet, Microsoft Teams or Zoom link, a Telegram @group / t.me link / chat_id / t.me/call slug, 'new' for a fresh Telegram conference, a WhatsApp group JID (digits@g.us), or a live session UUID to wake the agent on a running call. Omit only when passing thread_id.
agent_idYesID of an active agent in this workspace (from agents.list). Any active agent can be dispatched — a voice trigger is NOT required.
greetingNoFirst line the agent speaks on a 1:1 call. Omit to use the agent's configured default greeting.
thread_idNoInbox thread id of a RUNNING call — wakes the agent on the bot already in it. Alternative to a session UUID target.
vision_modeNoScreen-share capture mode (Meet + Telegram spawns): 'off', 'on_demand' (agent can call vision_query), 'continuous_0_3fps' (ambient scene captures each turn). OMIT to use 'off' (the default).
in_workspaceNoRun this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected.
instructionsNoTask brief for the agent, e.g. 'take notes and answer questions about the roadmap'. On a spawn it is woven into the voice system prompt; on a wake it is the kickoff turn the agent responds to. OMIT for a generic listening/greeting agent.
start_immediatelyNoSpawn routes only: if true the agent starts talking as soon as it joins instead of waiting to be addressed. OMIT (default false) to stay silent until addressed. Wake routes always speak immediately.
channel_account_idNoThe workspace account that places or joins the call (id from channels.list): the Telegram account, the WhatsApp number, the phone number. Optional with exactly one account of that channel. Telegram: required with several. WhatsApp group: with several numbers the one in the group calls; several of them in the group is refused with the list.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / target / description
      Previous value: -"Where to send the agent: a Google Meet or Microsoft Teams link, a Telegram @group / t.me link / chat_id / t.me/call slug, 'new' for a fresh Telegram conference, a WhatsApp group JID (digits@g.us), or a live session UUID to wake the agent on a running call. Omit only when passing thread_id."New value: +"Where to send the agent: a Google Meet, Microsoft Teams or Zoom link, a Telegram @group / t.me link / chat_id / t.me/call slug, 'new' for a fresh Telegram conference, a WhatsApp group JID (digits@g.us), or a live session UUID to wake the agent on a running call. Omit only when passing thread_id."
  2. Changed1 schema field changed
    • changedInput schema / properties / channel_account_id / description
      Previous value: -"Telegram routes: workspace Telegram account that joins/founds the call. Optional with exactly one Telegram account; required with several."New value: +"The workspace account that places or joins the call (id from channels.list): the Telegram account, the WhatsApp number, the phone number. Optional with exactly one account of that channel. Telegram: required with several. WhatsApp group: with several numbers the one in the group calls; several of them in the group is refused with the list."
  3. 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"
      +}
  4. Added

TDQS

A3.8/5.0
Behavior1/5

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

The description states the tool 'creates a NEW Telegram conference call', spawns bots into live meetings, and wakes agents on running calls — all state-changing effects. The annotations declare readOnlyHint=true (and destructiveHint=false, idempotentHint=true), which directly contradicts creating a conference call and joining a live call. This is an Annotation Contradiction; the otherwise-rich behavioral detail cannot be credited against a false read-only claim, because an agent may invoke it assuming no side effects.

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?

Long but dense and front-loaded: the router table comes first, then prerequisites, then the sibling escape hatches, each in a short clause. Some content duplicates the input schema's parameter descriptions (target routing, instructions behavior), which is the only real redundancy. Nearly every sentence carries a decision-relevant fact.

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?

Ten parameters, one required, no output schema — so the description must carry routing, prerequisites, and lifecycle, and it does: it covers all target shapes, the wake-versus-spawn distinction, agent validity, account selection, and adjacent tools for translator and dismissal. The one return value it produces ('returns its shareable link') is named for the only route that returns something.

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 every parameter already carries its own explanation, including target routing, wake semantics, and the multi-account channel_account_id rules. The description reinforces key semantics ('Always pass agent_id', 'Omit only when passing thread_id', active-agent requirement) but adds little meaning beyond what the schema already states. Baseline 3 applies when the schema does the heavy lifting.

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 ('Send a workspace AI agent into a live call') and then does the harder work of enumerating every routing surface the single `target` parameter covers — Meet/Teams/Zoom link, Telegram group or slug, 'new' conference, WhatsApp JID, session UUID/thread_id. An agent can predict the effect of a call for each input shape 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 Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit when-to-use and when-not-to-use guidance: a live translator goes to calls.dispatch_translator, removing the agent afterwards goes to calls.dismiss_agent, and the wake-vs-spawn rule is stated for both meeting links and session UUIDs. Prerequisites are also given (agent_id from agents.list, must be an ACTIVE agent, system templates refused and must be cloned via agents.create).

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.