KaiCalls

Make Call

make_call

Destructive

Place an outbound call through a KaiCalls AI agent: a voice preview so the owner can hear Kai, or a call made on the owner's behalf (a landlord, clinic, pharmacy, school or utility) with the task in context. A call never proves inbound routing or advances activation. When the person asking writes in another language, pass report_language so Kai gathers exact details and the result is relayed in that language; Kai speaks call_language (English by default) on the phone. Requires a plan with a card on file. Pass an idempotency_key to make the request safely retryable.

Input Schema

TableJSON Schema

Name	Required	Description
`to`	Yes	Phone number to call (E.164 format, e.g. +19085551234)
`name`	No	Caller/lead name (optional)
`context`	No	Call context or reason (optional)
`lead_id`	No	Existing lead ID to associate (optional)
`agent_id`	Yes	KaiCalls agent ID to use for the call
`call_language`	No	Language Kai speaks on the call (optional, default en)
`first_message`	No	Override the agent greeting message (optional)
`idempotency_key`	No	Client-chosen key that makes this call exactly-once: retries with the same key never place a second call (optional but recommended)
`report_language`	No	Language the person asking reads, as a code or name (e.g. ar, ht, tr, bn, es, zh, vi). Kai confirms names, dates and numbers so the result can be relayed in this language (optional)
`connector_activation_call`	No	True only for the one-time connector activation call the recipient explicitly requested in this conversation. This is not permission for marketing, SMS, or future calls.

Output Schema

TableJSON Schema

Name	Required	Description
`call`	No
`error`	No	Present when success is false
`success`	Yes	Whether the tool completed successfully
`replayed`	No
`intent_id`	No
`preview_only`	No
`call_language`	No
`idempotency_key`	No
`report_language`	No
`counts_toward_activation`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedSep 30, 2026

addedInput schema / properties / call_language

Added value: +{
+  "description": "Language Kai speaks on the call (optional, default en)",
+  "enum": [
+    "en",
+    "es"
+  ],
+  "type": "string"
+}

addedInput schema / properties / report_language

Added value: +{
+  "description": "Language the person asking reads, as a code or name (e.g. ar, ht, tr, bn, es, zh, vi). Kai confirms names, dates and numbers so the result can be relayed in this language (optional)",
+  "type": "string"
+}

addedOutput schema / properties / call_language
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / report_language
```
Added value: +{
+  "type": "string"
+}
```

Changed3 schema fields changedSep 10, 2026

addedInput schema / properties / connector_activation_call

Added value: +{
+  "description": "True only for the one-time connector activation call the recipient explicitly requested in this conversation. This is not permission for marketing, SMS, or future calls.",
+  "type": "boolean"
+}

addedOutput schema / properties / counts_toward_activation
```
Added value: +{
+  "type": "boolean"
+}
```
addedOutput schema / properties / preview_only
```
Added value: +{
+  "type": "boolean"
+}
```

Changed4 schema fields changedJul 21, 2026

addedInput schema / properties / idempotency_key

Added value: +{
+  "description": "Client-chosen key that makes this call exactly-once: retries with the same key never place a second call (optional but recommended)",
+  "type": "string"
+}

addedOutput schema / properties / idempotency_key
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / intent_id
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / replayed
```
Added value: +{
+  "type": "boolean"
+}
```

AddedJun 22, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare destructiveHint=true and openWorldHint=true. The description adds meaningful behavioral context beyond them: the card-on-file prerequisite, the 'never advances activation' limitation, and how idempotency_key makes the request exactly-once. The idempotency claim does not contradict idempotentHint=false, since it clarifies that a key is required to achieve retry safety.

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?

A single dense paragraph that front-loads the two modes and requires no preamble, with each sentence carrying operational content (prerequisite, activation caveat, language semantics, idempotency). It is on the longer side but almost nothing is filler.

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?

With annotations, a full output schema, and 100% schema coverage already present, the description supplies the missing operational context: prerequisites, the activation caveat, and language handling. An agent could call this correctly; only explicit sibling routing remains unaddressed.

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, but the description adds genuine meaning: it explains the subtle report_language (language of the person asking) versus call_language (language Kai speaks) distinction that the schema alone leaves implicit. This is a real semantic contribution over the field docs.

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+resource ('Place an outbound call through a KaiCalls AI agent') and then enumerates the two distinct modes (voice preview vs. call on the owner's behalf). This clearly separates it from siblings like check_call_status, list_recent_calls, and send_sms without needing their schemas.

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 real usage context: the prerequisite 'Requires a plan with a card on file', the note that 'A call never proves inbound routing or advances activation', and the two call modes. It doesn't explicitly name a sibling alternative (e.g. send_sms vs. make_call in multilingual cases), so it stops short of a 5.

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

All KaiCalls tools Inspect

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.