Skip to main content
Glama
callcenter-kpi-mcp

callcenter-kpi-mcp

by jojao115

Comparar empresas

comparar_empresas
Read-only

Compare companies side by side over a date range, returning volume, abandonment rate, TME, TMA, average CSAT and percentage of satisfied contacts. Use it to benchmark call center performance across companies.

Instructions

Põe as empresas lado a lado num período: volume, taxa de abandono, TME, TMA, CSAT médio e % de satisfeitos.

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": "comparar_empresas"
  }
}

Input Schema

NameRequiredDescriptionDefault
data_fimNoÚltimo dia, incluído, AAAA-MM-DD. Padrão: ontem.
data_inicioNoPrimeiro dia, AAAA-MM-DD (fuso de São Paulo). Padrão: 7 dias antes de data_fim.

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?

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds real value by disclosing which metrics are returned, which matters because there is no output schema. It says nothing, however, about how companies are ordered, whether companies without data are omitted, or the aggregation basis for CSAT and % de satisfeitos.

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?

A single sentence with no filler, front-loaded with the comparison action and then the metric list. It is appropriately sized for a two-parameter read tool; the only mild inefficiency is that the metric enumeration is compressed into one chain rather than clearly delimited.

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 read-only aggregation with two optional, fully described date parameters and no output schema, the description covers both the action and the returned fields, which is most of what an agent needs. It leaves open which set of companies is compared (there is no company filter parameter) and whether ordering or row limit applies.

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%: both date parameters carry patterns, defaults and the São Paulo timezone note. The phrase 'num período' only gestures at these two parameters and adds no format or behavior detail beyond the schema, so the baseline 3 applies.

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?

'Põe as empresas lado a lado num período' gives a specific verb (compare/put side by side) and resource (empresas), then enumerates the exact metrics produced (volume, taxa de abandono, TME, TMA, CSAT médio, % de satisfeitos). This clearly distinguishes a multi-company multi-metric comparison from siblings like volume_por_hora or csat_por_operador, though no sibling is named explicitly.

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 'lado a lado' and 'num período' suggest a cross-company comparison over a date window. There is no explicit when-to-use statement, no named alternative (e.g. listar_empresas for a plain listing), and no exclusion or prerequisite.

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