Skip to main content
Glama

dialogbrain

by io.github.saloprj
OverviewDiscussionsAdmin

calls_agent_duel

Start an agent-vs-agent VOICE test call: two AI voice agents share one LiveKit room — a 'caller' persona agent pursues a task brief against the 'callee' business agent under test. Use to evaluate booking flows, latency, and conversation quality without a human caller.

The CALLER agent should have an EMPTY voice_greeting (it must stay silent until the callee greets) and voice_filler_enabled=false. Afterwards inspect both call_ids with agents.traces_list / calls.get_transcript. A subscribe-only listen token is returned for listening in live.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
taskYesThe caller's brief — objective, persona details (name, phone), and when to end the call. Woven into its prompt as call instructions.
in_workspaceNoRun this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected.
max_duration_sNoHard cap on the call in seconds (30-900, default 300).
callee_agent_idYesAgent under test (answers and greets first). From agents.list.
caller_agent_idYesCustomer-persona agent that places the call. Must be a different agent, active, with empty voice_greeting.

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
  3. Removed
  4. Added

TDQS

A4.1/5.0
Behavior4/5

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

Annotations cover the safety profile (readOnly=false, destructive=false, idempotent=false). The description adds real operational context the annotations don't carry: the caller must be a different, active agent with empty voice_greeting and voice_filler_enabled=false (it stays silent until greeted), plus a subscribe-only listen token for live monitoring.

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 core action, then a second paragraph of prerequisites and follow-up. Dense but every sentence earns its place; minor tightening possible in the caller-config sentence.

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?

Covers the full workflow: pre-call caller configuration, live monitoring via the returned listen token, and post-call inspection of both call_ids. With no output schema, the mention of returned tokens and call_ids is valuable; a bit more on what a completed duel produces would complete it.

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 baseline is 3. The description reinforces the caller-agent constraints (empty greeting, filler disabled) but adds little syntactic meaning beyond the already-documented parameters.

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?

Specific verb+resource: 'Start an agent-vs-agent VOICE test call' with the two roles (caller persona vs callee business agent under test) and the LiveKit room mechanism spelled out. This clearly distinguishes it from single-agent siblings like calls_make and calls_dispatch_agent.

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?

'Use to evaluate booking flows, latency, and conversation quality without a human caller' gives a clear when-to-use condition. It also names the follow-up tools (agents.traces_list / calls.get_transcript) but stops short of explicitly contrasting with the nearest siblings (calls_make, agents_simulate_inbound).

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