Sautikit

handoff_dialer_call

SPENDS MONEY: send one waiting answered caller to a published AI agent; the AI minutes bill the workspace wallet. Works once per caller and only while they are still waiting; a caller already connected, already with an AI or who hung up returns dialer.invalid_state (409). NEVER call this without explicit human confirmation naming the caller (from get_dialer_live) and the agent.

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": {
      "attempt_id": "<attempt_id>",
      "agent_id": "<agent_id>"
    },
    "name": "handoff_dialer_call"
  }
}

Input Schema

Name	Required	Description
`purpose`	No	Required on tools that read data or reports; recommended on every tool. One sentence: what you are doing and why (for example "finding this caller's open ticket to answer them"). Building a report, dashboard, analytics or an export is a SautiDesk Pro feature done by the report tools, not by pulling records.
`agent_id`	Yes	UUID of a published AI agent of this workspace
`attempt_id`	Yes	the waiting caller's attempt_id from get_dialer_live

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 5, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Goes well past the annotations by disclosing that AI minutes bill the workspace wallet, that the operation succeeds only once per caller and only in the waiting state, and the exact failure code returned otherwise. The destructiveHint=false annotation is not contradicted, since the tool re-routes a live call rather than destroying data, and the cost warning supplements rather than conflicts with it.

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?

The cost warning is front-loaded in caps, followed by the action, then the state constraints, then the confirmation rule. Three dense sentences with no filler and nothing that repeats the schema verbatim.

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 costly, irreversible-ish state change with no output schema, it covers cost, idempotency, preconditions, and the error path. It does not say what a successful handoff returns or where to discover a valid agent_id (e.g. list_agents), which is a minor remaining gap.

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 coverage is 100%, so both required parameters are already documented in the schema (attempt_id from get_dialer_live, published agent UUID). The description only reinforces that the confirmation must name the caller and the agent; it adds no new syntax, format, or sourcing detail beyond that. Baseline 3 applies.

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?

States a specific verb and resource ('send one waiting answered caller to a published AI agent') with tight scope qualifiers (one caller, answered, waiting). It does not name a competing sibling such as send_agent_call or desk_transfer_call, so the agent must infer the boundary from 'published AI agent' versus human transfer.

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?

Explicitly states the precondition (caller must be answered and still waiting), the invalidity condition (already connected, already with AI, or hung up returns dialer.invalid_state 409), the one-shot limit, and a hard prerequisite: never call without explicit human confirmation naming the caller and agent. That is an unambiguous when/when-not rule set.

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

All Sautikit 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.

Resources

Need Help?