Skip to main content
Glama

Place an outbound call

outbound_call
Destructive

Places one outbound voice call from one of the organisation's own numbers (caller ID) to a destination number; the business's AI agent handles the call. With dryRun: true it returns the call that would be placed, without dialling.

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": {
      "to": "<to>"
    },
    "name": "outbound_call"
  }
}

Input Schema

NameRequiredDescriptionDefault
toYesDestination number in international format
fromNoCaller ID to dial from: one of the numbers this organisation owns. Defaults to the organisation's default caller ID when unset.
dryRunNo
headersNoOptional SIP/routing headers
businessIdNoBusiness/org id (defaults to the token's org)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / from / description
      Previous value: -"Caller ID to dial from. Must be a number this organisation owns — call caller_ids first to see which, and ask the user which to use rather than guessing. Defaults to DEFAULT_CALLER_ID when unset."New value: +"Caller ID to dial from: one of the numbers this organisation owns. Defaults to the organisation's default caller ID when unset."
  2. First observed

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, openWorldHint=true and non-idempotency, so the safety profile is carried by structured data. The description adds real context beyond that: the caller ID must be an org-owned number and dryRun gives a no-dial preview. It still omits the practically important traits — that a real phone will ring, cost implications, and that repeated calls create separate calls (non-idempotent) — which matter more than the annotation flags for a live dialling tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences: the core action and scope first, the dryRun exception second. Nothing is repeated from the schema and no sentence is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a five-parameter, open-world mutating tool with no output schema, the definition covers what the tool does and the dryRun preview, but leaves the success result (returned call identifier), cost/latency expectations and error conditions for owned-number validation 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 80%, but the one undescribed parameter, dryRun, is exactly what the description explains in behavioural terms. It also reinforces that `from` must be an organisation-owned number, adding constraint semantics beyond the schema's wording. The `headers` parameter remains unexplained in both places.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb and resource ('Places one outbound voice call') plus meaningful scope: the call originates from the organisation's own caller ID and is handled by the business's AI agent. It is clear enough to separate from hangup_call, call_status and call_list, though it never names a sibling to contrast against.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

Usage is only implied — you call this when you want to dial someone — but there is useful guidance for the dryRun mode ('returns the call that would be placed, without dialling'). It says nothing about when not to use it, prerequisites such as ownership of the caller ID being validated elsewhere, or how it relates to campaign/contact tools.

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.