Skip to main content
Glama
hajekd
by hajekd

scan_calls

AI-score calls in a date range to identify angry customers, compliance issues, or missed commitments. Returns a ranked list with summaries for review.

Instructions

AI-score answered calls in a date range. Returns one page of scored results.

IMPORTANT: Before calling this tool, briefly tell the user that this analysis takes some time because it processes each call with AI (e.g. "Let me analyze your calls — this involves AI-scoring each conversation, so it may take a moment.").

Fetches a page of calls (default 100), loads their transcripts, scores each with a fast AI model, and returns a compact ranked list with scores, flags, and summaries.

CRITICAL — you MUST scan ALL pages. The first 100 results are NOT representative of the full dataset. Important issues may appear in any page. If the response shows remaining records, you MUST call all remaining pages (in parallel) before presenting results. Never skip pages or stop early — partial analysis gives unreliable results.

Pagination: Each call returns up to take scored records and reports the total. If total > take, call ALL remaining pages IN PARALLEL:

  • First call: scan_calls(date_from='2026-02-20') → returns 100 scored + "350 total"

  • Then IN PARALLEL: scan_calls(..., skip=100), scan_calls(..., skip=200), scan_calls(..., skip=300)

After reviewing scored results, use get_call_transcript to read full dialogue of specific flagged calls.

Args: date_from: Start date (YYYY-MM-DD). Required. date_to: End date (YYYY-MM-DD). Defaults to same as date_from (single day). user: Agent name — display name or login name, resolved automatically. queue: Queue internal name (e.g. '10333'). question: What to analyze for. Be specific about what to flag. skip: Pagination offset (default: 0). Use to fetch subsequent pages. take: Number of calls to score in this page (default: 100, max: 200).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
skipNo
takeNo
userNo
queueNo
date_toNo
questionNoFlag calls needing management attention: angry customers, escalation requests, compliance issues, lost deals, missed commitments.
date_fromYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior5/5

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

With no annotations provided, the description fully discloses behavioral traits: it takes time, processes each call with AI, returns only one page, and requires iterating through all pages for reliable results. It also explains that the first page may not be representative, which is critical for safe and accurate use.

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?

The description is long but well-structured with headings, bolded warnings, and bulleted examples. It is front-loaded with the core purpose and important caveats. There is minor redundancy between the CRITICAL warning and the Pagination section, but every part serves a purpose.

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?

The description covers the full context: what it returns, pagination behavior, parallel call requirements, and the follow-up tool. Given the tool's complexity (AI scoring, pagination, user communication), this is complete enough for an agent to invoke it correctly without additional context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has no parameter descriptions, but the description compensates with an 'Args' section covering all 7 parameters, including formats, defaults, and examples (e.g., queue: '10333', date_from: 'YYYY-MM-DD'). This adds meaning well beyond the raw schema.

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?

The description clearly states the tool's purpose: 'AI-score answered calls in a date range. Returns one page of scored results.' This uses a specific verb and resource, and distinguishes it from sibling tools like list_calls or get_call_transcript by emphasizing AI scoring and pagination.

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?

The description provides strong usage guidance: it instructs the agent to warn the user about processing time, mandates scanning all pages, and names get_call_transcript as a follow-up tool for reading full dialogues. It could be clearer about when to use list_calls instead, but the guidance is otherwise explicit.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/hajekd/mcp-daktela'

If you have feedback or need assistance with the MCP directory API, please join our Discord server