Skip to main content
Glama

Get voice campaign report

get_voice_campaign_report
Read-onlyIdempotent

Per-agent results of one voice campaign: contacts handled, calls left without a disposition (timeout) and the average handle time in seconds, plus the campaign-wide average. An AI voice campaign (handler_type voice_ai) also has ai: calls placed and answered, AI minutes, transfers to people, voicemails, opt-outs, hot leads, call backs still due, the contacts per disposition and by_decided_by (who decided each outcome: ai_agent, jev = an AI check during the call, post_call = the summary, human, system). ai.dial_causes counts the calls that reached nobody by cause (voicemail_detected, busy, declined, unavailable, no_answer, number_not_found, no_route, carrier_rejected, timeout, platform_error, unknown) and ai.unreached splits the contacts not reached into failed, no_answer, voicemail, no_conversation (the call broke off during the opening, or its summary was undetermined) and other. ai.undecided counts the calls that ended with no disposition (neither the AI agent nor the summary chose one) by reason: undetermined, missing, unknown (a key the campaign does not have), failed (no summary). A campaign that chains people per group (for example a company whose authorized people are called one after another) also has fallback_groups: groups reached and at which person (reached_by_order), still open, not reached, and with no valid number. interest.counts counts the contacts by interest (interested, undecided, not_interested, not_presented) and interest.interested_groups the groups with someone interested (null without groups). ai.answered_by_person counts the calls a person picked up, while ai.answered also counts voicemail, call screeners and carrier announcements.

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": {
      "campaign_id": "<campaign_id>"
    },
    "name": "get_voice_campaign_report"
  }
}

Input Schema

NameRequiredDescriptionDefault
fieldsNoOptional: return only these fields of each record.
campaign_idYesCampaign id as returned by list_voice_campaigns.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / fields / items / enum
      Previous value: -[
      -  "agents",
      -  "avg_handle_time_secs",
      -  "ai",
      -  "fallback_groups"
      -]New value: +[
      +  "agents",
      +  "avg_handle_time_secs",
      +  "ai",
      +  "fallback_groups",
      +  "interest"
      +]
  2. Changed1 schema field changed
    • changedInput schema / properties / fields / items / enum
      Previous value: -[
      -  "agents",
      -  "avg_handle_time_secs"
      -]New value: +[
      +  "agents",
      +  "avg_handle_time_secs",
      +  "ai",
      +  "fallback_groups"
      +]
  3. Added

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered and the description need not restate it. What the description adds is return-shape behavior, including conditional presence of the `ai` and `fallback_groups` blocks and the null case for interest.interested_groups, which is genuinely useful. It omits any access/permission requirements, error behavior, or pagination/limits.

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

Conciseness3/5

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

The single most important clause is front-loaded, and nearly every clause carries real information about a returned field, which is defensible because there is no output schema. However, the whole definition is one extremely long run-on sentence with deeply nested parentheticals, and there are no breaks to separate the base record shape from the conditional ai/fallback_groups/interest blocks.

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?

With no output schema, the description must carry the return-value burden, and it does so thoroughly, including conditional blocks per campaign type and the meaning of ambiguous counters like answered versus answered_by_person. The remaining gap is operational: nothing about permissions, behavior on a non-existent campaign_id, or whether the human-campaign case simply omits `ai`.

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% for both parameters, so the schema already explains campaign_id and the `fields` filter. The description does not name or explain the `fields` parameter at all, though its enumeration of sections (agents, average handle time, ai, fallback_groups, interest) happens to mirror the enum values, giving an implicit mapping. This is baseline-level value rather than added meaning.

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 opens with a specific verb-object framing: 'Per-agent results of one voice campaign,' followed by the exact metrics returned (contacts handled, timeout calls, average handle time). That is clear enough to know what the tool produces, but it never contrasts itself with nearby siblings such as get_voice_campaign or get_agent_report, so the agent must infer that this is the per-agent breakdown report rather than the campaign config or a single-agent report.

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

Usage Guidelines2/5

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

There is no explicit when-to-use statement, no exclusions, and no named alternative. The only usage signal is indirect: the conditional note that a 'handler_type voice_ai' campaign 'also has ai', which tells the agent something about applicability but not when to choose this tool over the other report 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.

Resources