Skip to main content
Glama
keycrm-mcp

keycrm-mcp

by IgorShutko

publications

Lists marketplace publications with status and product columns, and retrieves per-marketplace variations for a given publication ID.

Instructions

Marketplace publications (публікації): list, variations.

Actions: list - publications with marketplace/status/product columns variations - publication_id required, per-marketplace variations Empty on this tenant (no marketplaces connected). Sync/load actions are omitted on purpose: they push products to a live marketplace.

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": "publications"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNo
limitNo
actionNolist
filtersNo
publication_idNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations present, the description carries the behavioral burden itself and does a fair job: it discloses the tenant-state caveat (no marketplaces connected, so results are empty), names the deliberately withheld mutating actions and why, and describes what the list output contains. It stops short of stating pagination behavior or explicit read-only status for the two included actions.

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 and an action list, then caveats. Structure with per-action bullets is easy to scan; the Cyrillic gloss and tenant note are short and earn their place. Slight redundancy between the header action list and the parameter's default value.

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?

Output schema exists, so return values need not be described, and the action semantics are covered. However, for a 5-parameter tool with zero schema description coverage, leaving 'filters' and the pagination params undefined leaves a real gap an agent cannot close from structured fields alone.

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% and no parameter is required, so the description must compensate. It adds the valid values for 'action' (list/variations, absent from the schema as an enum) and the conditional requirement on publication_id, but leaves 'page', 'limit' and especially the free-form 'filters' object completely unexplained.

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?

States a specific resource (marketplace publications) and enumerates the two supported operations (list, variations) with the columns list returns. An agent can tell this is the read-only publications surface, though it is not explicitly contrasted with the sibling 'products' tool.

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?

Gives real conditional guidance: 'variations' requires publication_id, and the description explains that sync/load actions are deliberately omitted because they mutate a live marketplace, which tells the agent not to look for write operations here. It also warns the tenant returns empty, which heads off confusion. No explicit routing versus 'products' is offered.

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