Skip to main content
Glama

dialogbrain

by io.github.saloprj
OverviewDiscussionsAdmin

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 or Microsoft Teams 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.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
titleNotarget='new' only: label for the new conference.
targetNoWhere 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.
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_idNoTelegram routes: workspace Telegram account that joins/founds the call. Optional with exactly one Telegram account; required with several.

Schema Changelog

Changes observed during successful MCP inspections.

  1. 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"
+}
  2. Added

TDQS

A3.7/5.0
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' and sends agents into live calls, which contradicts the annotation readOnlyHint=true. Three other hints (openWorld, idempotent, non-destructive) are consistent with the described wake-instead-of-double-join behavior, but the readOnly conflict is a genuine safety-signal mismatch that could lead an agent to dispatch without confirming 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?

Front-loaded with the action and the routing decision, then qualified with wake-vs-spawn, the required agent_id, and the translator alternative. It is dense rather than padded, though it re-lists the `target` values almost verbatim from the schema, which is redundant for an agent that can read both.

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 10-parameter, 6-route dispatch tool with no output schema, the description covers every routing branch, the wake-vs-spawn distinction, and the one return value it exposes ('returns its shareable link'). It omits failure/prerequisite behavior (e.g., whether the call must be live, permission requirements, what happens when the target is unreachable), which keeps it short of a 5.

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 the schema already documents all 10 parameters, including the full `target` enumeration, and the description largely restates that same routing list. It adds a little genuine guidance (agent_id provenance, thread_id as an alternative to a session UUID, translator routing), but not enough to exceed the baseline when the schema carries the load.

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?

Names a specific verb and resource ('Send a workspace AI agent into a live call') and immediately disambiguates the router with 'ONE tool for every surface; `target` decides where'. The enumerated surfaces (Meet/Teams link, Telegram group/chat_id/t.me/call, 'new', WhatsApp JID, session UUID, thread_id) let an agent distinguish this tool from siblings like calls_dispatch_translator without opening a 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: 'For a live TRANSLATOR use calls.dispatch_translator instead', 'Always pass agent_id (from agents.list)', and it points to calls.list_active as the source of a session UUID. It also states the wake-vs-spawn rule and its fallback ('the router also checks for a bot already in that meeting and wakes it rather than double-joining'), leaving nothing to inference.

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

All dialogbrain toolsInspect
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.

Resources