Dialpad MCP server

dialpad_create_stats_export

Read-only

Start a Dialpad analytics export as raw records or summary stats for calls, texts, voicemails, recordings, on-duty, CSAT, or dispositions, then poll with the returned request_id for the download link.

Instructions

Start a Dialpad analytics export (calls, texts, voicemails, recordings, on-duty, CSAT, dispositions) as raw records or summary stats, then poll dialpad_get_stats_export with the returned request_id for the download link. Starts a report job only; changes no Dialpad data. Dialpad allows about 200 per hour. Contains personal information - admin-gated.

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": {
      "export_type": "<export_type>",
      "stat_type": "<stat_type>"
    },
    "name": "dialpad_create_stats_export"
  }
}

Input Schema

Name	Required	Description
`group_by`	No	Grouping for stats exports.
`is_today`	No	Export today only.
`timezone`	No	Time zone name, e.g. Australia/Sydney (default UTC).
`office_id`	No	Limit to one office (ignored when a target is set).
`stat_type`	Yes	What to export. csat and dispositions need target_id and target_type, and records only.
`target_id`	No	Limit to one target. Needs target_type.
`export_type`	Yes	records = one row per item; stats = summary.
`target_type`	No	Type of target_id.
`days_ago_end`	No	End of the range, in days ago (default 30).
`days_ago_start`	No	Start of the range, in days ago (default 1).

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 14, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false; the description reinforces this ("Starts a report job only; changes no Dialpad data"), which is consistent and useful. It adds genuinely non-structured context: the ~200/hour rate limit, admin gating, and that the output contains personal information. It does not spell out whether repeated calls create duplicate jobs or how long exports persist, which is the remaining gap for a non-idempotent job-creator.

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 tight sentences: purpose and payload first, the follow-up call second, safety/limits last. No filler, and the most decision-relevant information is front-loaded.

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

Completeness5/5

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

For a 10-parameter, non-idempotent job-creation tool with no output schema, the description covers the async handoff, the safety profile, auth gating, and rate limits. Defaults for the day-range parameters live in the schema, so 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%, so all ten parameters are already documented, including the records/stats distinction and the csat/dispositions target_id requirement. The description's enumeration of exportable data types mirrors the stat_type enum rather than adding new meaning. Baseline 3 applies since the schema carries the parameter burden.

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?

Specific verb+resource ("Start a Dialpad analytics export") with the exported data domains enumerated (calls, texts, voicemails, recordings, on-duty, CSAT, dispositions) and the records-vs-stats shape named. It explicitly separates itself from the sibling reader by naming dialpad_get_stats_export as the polling step.

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?

The description gives an explicit two-step workflow: create here, then poll dialpad_get_stats_export with the returned request_id for the download link. It also states the operational constraints that gate usage (about 200/hour, admin-gated), so an agent knows both the sequence and the preconditions.

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