Sautikit

send_agent_call

SPENDS MONEY: place ONE AI agent call now (bypasses broadcast scheduling; billed per second for telco + AI). Always confirm the destination number with the user first. Returns call_id — follow up with get_call.

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": {
      "agent_id": "<agent_id>",
      "to": "<to>",
      "prompt_template": "<prompt_template>"
    },
    "name": "send_agent_call"
  }
}

Input Schema

Name	Required	Description
`to`	Yes	destination phone, strict E.164 with leading +
`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	agent UUID
`revision`	No	pin a published revision; omit to use the current draft
`variables`	No	values for the template placeholders
`prompt_template`	Yes	per-call prompt; {{variable}} placeholders filled from variables

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?

Annotations only cover title and openWorldHint/destructiveHint, so the description carries the important disclosure burden and does it: it flags that the call spends money, that billing is per-second for telco plus AI, that scheduling is bypassed, and what is returned (call_id). That is exactly the risk context an agent needs before invoking a paid write action.

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?

Three short sentences, risk warning front-loaded in caps, then the action, then the return value. No filler, and the most decision-relevant fact is first.

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 6-parameter paid mutation with nested 'variables' and no output schema, the description covers cost, precondition, scope, and return value adequately. Minor gap: it does not clarify draft-vs-published revision behavior beyond what the schema states, but nothing essential is missing.

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%, including detailed guidance on 'to' (strict E.164) and 'purpose', so the schema does the heavy lifting. The description only reinforces that the destination number must be confirmed with the user; it adds nothing about revision pinning or variables beyond what the schema already says.

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 and resource ('place ONE AI agent call now') and immediately scopes it apart from the broadcast/campaign path ('bypasses broadcast scheduling'), which is the main ambiguity among the many call-related siblings.

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 a clear precondition ('Always confirm the destination number with the user first') and a follow-up path ('follow up with get_call'), plus the implicit routing rule that scheduled/bulk calls belong to broadcasts rather than this tool. It stops short of naming other one-off call siblings such as place_call or desk_place_call.

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?