Skip to main content
Glama
keycrm-mcp

keycrm-mcp

by IgorShutko

delivery

Look up connected carriers, prep centers, warehouses, locations, and street addresses; estimate shipment prices and preview waybills without creating shipments.

Instructions

Delivery (доставка): connected services, prep centers, templates, carrier lookups.

Actions: services - connected delivery services (empty on this tenant) prep_centers - packing/prep centers, paginated prep_centers_active - active prep centers shipment_templates - waybill templates warehouses - carrier warehouse/office list: Nova Poshta, Ukrposhta and Meest need location_ref (from locations), Rozetka takes query locations - carrier city/place search for service + query streets - Nova Poshta street search: query + location_ref suggest - address suggestion by query (500 on this tenant) price - POST shipment-price for order_id on service (dry run) print - GET waybill document for order_id on service (text preview) service: novaposhta, novaposhta_international, ukrposhta, meest_express, rozetka, rozetka_delivery, dhl_express, fedex, ups. This tool never creates a shipment; that would push data to a carrier.

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": "delivery"
  }
}

Input Schema

NameRequiredDescriptionDefault
dataNo
pageNo
limitNo
queryNo
actionNoservices
filtersNo
serviceNo
order_idNo
location_refNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description does real work: it states the tool never creates a shipment, that 'price' is a POST shipment-price dry run, that 'print' returns a text preview, and it flags tenant-specific failures ('empty on this tenant', '500 on this tenant'). It omits auth requirements, rate limits, and pagination semantics beyond the word 'paginated'.

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 resource summary, then a scannable action list with aligned two-space formatting and a closing constraint. Dense but every line conveys an action or a constraint; no filler sentences.

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?

Output schema exists, so return values need not be described, and the description covers the action space plus key failure modes. The residual gap is the undocumented 'data' and 'filters' escape-hatch parameters and the service enum not being enforced in the schema.

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% across 9 parameters, so the description must compensate. It maps action, service (with an actual carrier list), order_id, location_ref, and query to specific actions well, but 'data' and 'filters' are never explained, and page/limit are only implied by 'paginated'.

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 gives a specific resource domain (delivery: connected services, prep centers, templates, carrier lookups) and then enumerates every action with a concrete object, including carrier-specific behaviors like 'warehouses' for Nova Poshta/Ukrposhta/Meest/Rozetka. An agent can tell this is the carrier/delivery integration surface and distinguish it from sibling namespaces like orders or products.

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?

Each action carries a usage condition: warehouses 'need location_ref (from locations), Rozetka takes query', locations needs 'service + query', streets needs 'query + location_ref'. The closing line 'This tool never creates a shipment; that would push data to a carrier' is an explicit when-not boundary. It stops short of naming an alternative tool for creating shipments, so it is not a full 5.

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