Sautikit

create_dialer_campaign

Create a DRAFT drip dialer campaign (does not dial anyone). Set caller_id, callback_url, release rate, concurrency, DND hours, retries, a hard budget and AMD (on_machine leave_message needs amd.machine_message). The response includes callback_secret, the key that signs the answer callback: it is shown ONCE, so give it to the user to store. Add contacts, then start.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "create_dialer_campaign"
  }
}

Input Schema

Name	Required	Description
`amd`	No	answering-machine detection: {mode:off\|detect\|detect_and_act,on_machine:hangup\|leave_message\|mark_only,max_analysis_seconds,machine_message: text spoken to a machine, required (max 500 chars) when on_machine is leave_message}
`mode`	No	drip (default); progressive and predictive need the Pro plan
`name`	No	campaign label (avoid PII)
`hours`	No	DND hours: {windows:[{days:[1..5],start_minute,end_minute}],blackouts:[YYYY-MM-DD],timezone}
`retry`	No	retry policy: {max_attempts,backoff_minutes:[..],retry_on:[no_answer,busy,failed,voicemail,machine],min_gap_minutes,ordering:fifo\|best_time}
`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.
`timezone`	No	IANA timezone, e.g. Africa/Nairobi
`warn_pct`	No	percent of budget that fires dialer.budget.warning (1 to 100)
`caller_id`	No	E.164 number on this workspace to dial from
`ratio_max`	No	predictive only: most calls out per free agent, 1.0 to 3.0 (default 1.5)
`budget_minor`	No	hard campaign budget in minor currency units; dialing stops when it is spent
`callback_url`	No	https URL on a public host (no localhost or private addresses) that receives the answer event and returns the verbs to run
`max_concurrent`	No	most calls in flight at once, 1 to 200 (default 20)
`abandon_target_pct`	No	predictive only: abandon percentage the pacing holds to, 0.1 to 10 (default 3)
`daily_budget_minor`	No	daily budget in minor currency units
`release_rate_per_sec`	No	calls released per second, 0.01 to 10 (default 1)

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 5, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Goes well beyond the annotations (destructiveHint=false, openWorldHint=false) by disclosing that the campaign is inert until started, that the budget is hard and halts dialing when spent, that callback_url must be a public host, and that callback_secret is returned once and must be handed to the user for storage. The one-time secret disclosure is exactly the kind of non-obvious behavior an agent would otherwise miss.

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?

Three dense sentences with the most important constraint (draft, no dialing) front-loaded and the one-time secret warning placed where it will be read. The middle sentence is essentially a parameter list that partially duplicates the schema, which is the only waste.

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 16-parameter creation tool with no output schema, the description covers the non-obvious pieces: draft state, budget behavior, callback contract, and the post-creation workflow. It leaves minor gaps, such as whether a draft can be edited via update_dialer_campaign before starting and which fields are effectively mandatory despite zero required params.

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%, so the schema already documents every parameter including the AMD leave_message dependency. The description enumerates the same fields (caller_id, callback_url, release rate, concurrency, DND hours, retries, budget, AMD) without adding format or constraint detail beyond what the schema provides, so baseline 3 applies.

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 ("Create a DRAFT drip dialer campaign") plus the crucial scope qualifier "does not dial anyone," which separates it from start_dialer_campaign and update_dialer_campaign. An agent can identify the tool without opening the 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?

Gives an explicit sequencing workflow ("Add contacts, then start") that points the agent at add_dialer_contacts and start_dialer_campaign, and warns that progressive/predictive modes require the Pro plan. It stops short of naming when NOT to use this versus update_dialer_campaign for an existing draft.

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?