Skip to main content
Glama
keycrm-mcp

keycrm-mcp

by IgorShutko

report

Generates aggregated KeyCRM summaries for sales, leads, funnels, manager load, and stale cards across a date range or live pipeline data.

Instructions

Aggregate report over a date range (UTC, YYYY-MM-DD).

kind='sales' - orders: count, revenue (grand_total), average check, breakdown by status_id / manager_id / payment_status. kind='leads' - pipeline cards: count, sum of products_total, breakdown by status_id / pipeline_id / manager_id, plus finished/active split. kind='funnel' - live funnel: cards per status per pipeline, closed share and conversion percent (no date range needed, taken from the pipeline board). kind='managers' - load per manager: cards, closed, active, conversion, products_total. kind='stale' - cards with no updates for more than days (default 7) days.

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": "report"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNo
kindNosales
date_toNo
group_byNostatus
date_fromNo
max_itemsNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior3/5

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

With no annotations, the description carries the full burden; it discloses that dates are UTC/YYYY-MM-DD and that the funnel ignores the date range because it reads live from the pipeline board. It never states read-only safety, what happens when date_from/date_to are null (all-time?), or any cost/pagination behavior, leaving meaningful gaps.

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 general behavior, then one compact line per kind — every clause carries information. Minor density issue: kind names, metrics and grouping fields are packed with no visual separation, but nothing is redundant.

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

Completeness3/5

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

An output schema exists, so return values need not be described, and the five kinds are covered well. Completeness suffers for a 6-parameter tool where group_by and max_items are undefined in both schema and description, and the date-range defaults are unstated.

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 coverage is 0%, so the description must compensate: it thoroughly defines the kind enum, defines 'days' (default 7), and gives the date format. However group_by (default 'status') and max_items are never explained, and the null date defaults are left ambiguous, so roughly half the parameters remain undocumented.

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 first line names a specific verb and resource ('Aggregate report over a date range') and the per-kind breakdown makes clear this produces summaries rather than raw record lists, which distinguishes it from sibling tools like leads/orders. Each kind's metrics are enumerated so an agent knows exactly what the tool computes.

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 per-kind enumeration effectively tells the agent which kind to pick for sales, leads, funnel, manager load, or stale-card questions, and it explicitly notes funnel needs no date range. It does not name alternative tools or state exclusions, so it falls short of full when/when-not guidance.

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