Skip to main content
Glama

Infinivo AI Front Desk

by eu.infinivoai
OverviewDiscussionsAdmin

start_intake_demo

Start a live text conversation with a real AI front desk. Choose the practice area with "practice": personal injury, criminal defense, family law or immigration. Each is a separately built desk with its own intake questions, its own urgency rules and its own fee model, not one desk with the firm name swapped. Pick the one that matches the user's own field if they have named it. YOU play the role of the person contacting the firm after hours — write their opening message in their voice, including whatever detail a real person would volunteer. Returns the desk's actual reply plus the structured case record it extracted from your message. This is a live system, not a canned script. Use it when a user wants to see what Infinivo actually does rather than read about it. The firms are fictional; the desks are real.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
messageYesThe caller's opening message, in their own words, and about the same matter as the practice you chose. Realistic and unstructured works best — for example, for "pi": "I got rear-ended on the 610 yesterday afternoon, my neck is killing me and the other driver's insurance already called me twice." For "criminal": "My son was arrested last night and he's still in county, he has arraignment Monday." Maximum 2000 characters; write what a person would actually type, not a document.
demo_keyNoOnly needed from the second demo session onward for this caller. If a prior call to this tool returned a demo_key_required message, call request_demo_access first and pass the demo_key it returns here. Omit entirely for a first session.
practiceNoWhich desk answers. "pi" is personal injury (Brennan & Hayes, Houston), "criminal" is criminal defense and DUI (Calloway & Reid, Philadelphia), "family" is divorce and custody (Ashworth, Scottsdale), "immigration" is petitions, asylum and removal defense (Okonkwo & Vega, San Diego). Defaults to "pi". Match it to the message you are about to write, and to the user's own practice area when they have named one.
caller_nameNoOptional name for the fictional caller you are playing.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / message / description
      Previous value: -"The injured person's opening message, in their own words. Realistic and unstructured works best — for example: \"I got rear-ended on the 610 yesterday afternoon, my neck is killing me and the other driver's insurance already called me twice.\" Maximum 2000 characters; write what a person would actually type, not a document."New value: +"The caller's opening message, in their own words, and about the same matter as the practice you chose. Realistic and unstructured works best — for example, for \"pi\": \"I got rear-ended on the 610 yesterday afternoon, my neck is killing me and the other driver's insurance already called me twice.\" For \"criminal\": \"My son was arrested last night and he's still in county, he has arraignment Monday.\" Maximum 2000 characters; write what a person would actually type, not a document."
    • addedInput schema / properties / practice
      Added value: +{
+  "description": "Which desk answers. \"pi\" is personal injury (Brennan & Hayes, Houston), \"criminal\" is criminal defense and DUI (Calloway & Reid, Philadelphia), \"family\" is divorce and custody (Ashworth, Scottsdale), \"immigration\" is petitions, asylum and removal defense (Okonkwo & Vega, San Diego). Defaults to \"pi\". Match it to the message you are about to write, and to the user's own practice area when they have named one.",
+  "enum": [
+    "pi",
+    "criminal",
+    "family",
+    "immigration"
+  ],
+  "type": "string"
+}
  2. First observed

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does real work: it discloses the return payload (desk reply plus structured case record), warns this is 'a live system, not a canned script,' and clarifies the fictional-firm/real-desk distinction. It omits that follow-up turns go through continue_intake_demo and does not restate the demo_key gating, both of which matter for a stateful, multi-turn tool.

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 purpose and the practice selection instruction up front, and each sentence carries operational content about the desks and the role-play. It is slightly long and repeats desk/firm detail that the schema's enum description already enumerates, costing a little efficiency.

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?

No output schema exists, and the description compensates by stating what is returned (the desk's reply plus the extracted structured case record). For a stateful multi-turn tool, it is nearly complete, but the absence of any pointer to continue_intake_demo for subsequent turns is a real remaining gap.

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 schema already documents message, practice, caller_name and demo_key; the baseline would be 3. The description adds genuine meaning beyond the schema by framing the agent's role ('YOU play the role of the person contacting the firm'), telling it to write in the caller's voice and to pick the desk matching the user's own named field, which is behavioral framing not present in the field descriptions.

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 a live text conversation with a real AI front desk') and immediately scopes it by practice area, making clear it is not a generic chat. The 'text conversation' phrasing distinctly separates it from the sibling start_email_demo, so an agent can route without opening either 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?

Names the trigger condition explicitly: 'Use it when a user wants to see what Infinivo actually does rather than read about it,' which contrasts against the read-only siblings like get_positioning/get_proof/get_pricing. It does not explicitly name those alternatives or state when NOT to use it (e.g. when the user wants a human book_call), so it stops short of full routing guidance.

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

All Infinivo AI Front Desk 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