Skip to main content
Glama

get_call_insights

Generates a summary of analyzed customer calls over a date range, including call volume, sentiment, contact reasons, key moments, churn threats, and negative calls.

Instructions

Summary of the analyzed calls over a period: number of calls, minutes, mean customer sentiment, contact reasons, key moments, churn threats and the most negative calls. since / until: ISO dates, e.g. "2026-11-01" (until is exclusive). Read-only.

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": "get_call_insights"
  }
}

Input Schema

NameRequiredDescriptionDefault
sinceNo
untilNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior3/5

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

No annotations exist, so the description carries the full burden; it does declare "Read-only" and lists the aggregate metrics returned, which is useful. However, it omits key behavioral facts: what range is used when since/until are both null (both are optional with default null), whether results are paginated or bounded, and any cost/latency implications of a wide aggregation window.

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?

Front-loaded with the core purpose and the returned metrics, followed by a short parameter-format note and a trailing "Read-only" safety flag. Three compact sentences with no filler, though the enumerated metric list is long enough to slightly bury the parameter guidance.

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?

There is no output schema, so the enumeration of returned fields (counts, minutes, sentiment, reasons, moments, churn threats, most negative calls) is essential and present. The remaining gap is the undefined default time window when no dates are supplied, which matters for a period-scoped aggregate tool.

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?

With 0% schema description coverage, the description does real work: it documents both parameters as ISO dates, gives an example ("2026-11-01"), and states that until is exclusive — semantics the bare schema does not carry. It still leaves the default behavior undefined when either date is omitted, so compensation is partial rather than complete.

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?

"Summary of the analyzed calls over a period" names a specific resource (analyzed calls) and shape of result (aggregate summary), then enumerates the returned metrics: call count, minutes, sentiment, contact reasons, key moments, churn threats, most negative calls. An agent can tell it produces an aggregate rather than a per-call lookup (analyze_call) or an action list (suggest_actions), but it never explicitly contrasts with those siblings.

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

Usage Guidelines3/5

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

Usage is only implied: the word "Summary" plus "over a period" signals this is for aggregate/trend questions rather than single-call detail. There is no explicit when-to-use, when-not-to-use, or named alternative (e.g., "for a single call use analyze_call"), so the agent must infer routing from the output list.

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