Skip to main content
Glama
keycrm-mcp

keycrm-mcp

by IgorShutko

comments

Manage object notes on leads, orders, clients, or deals: list, add, edit, or delete entries with pagination in KeyCRM.

Instructions

Object comments (коментарі): list, add, edit, delete.

entity_type: lead, order, client or deal; entity_id is the CRM id of that object. Actions: list - comments of the object, paginated add - message required (or pass a full body in data) edit - comment_id required, new message or data body delete - comment_id required (the CRM keeps a soft-deleted flag)

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": "comments"
  }
}

Input Schema

NameRequiredDescriptionDefault
dataNo
pageNo
toneNonormal
limitNo
actionNolist
messageNo
entity_idNo
comment_idNo
entity_typeNolead

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations at all, the description carries the full burden. It does disclose one valuable trait beyond the schema: delete is a soft delete because the CRM keeps a deleted flag, and that list results are paginated. It does not say whether edit replaces or merges content, what happens when required fields are missing, or what the response looks like beyond the existence of an output schema.

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 short, front-loaded, and structured as an action list, so an agent can scan it quickly. The parenthetical localisation is harmless, but the action list mixes parameter requirements into the prose and is slightly uneven.

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 explained. With 9 parameters, 0% schema documentation, no annotations, and a completely undocumented tone parameter, the description is helpful but not complete enough for a multi-action CRUD tool.

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 explain them. It covers entity_type values, entity_id meaning, message, data body, and comment_id, which are the important ones. It never explains page, limit, or tone, and tone in particular is left completely opaque.

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?

The description states a specific resource (object comments) and the four operations it bundles (list, add, edit, delete), and it names the supported entity types (lead, order, client, deal), which scopes it to CRM objects. It never explicitly distinguishes itself from siblings such as tasks or documents, but the resource is distinct enough that confusion is unlikely.

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?

Per-action requirements are spelled out: add needs message or a data body, edit and delete need comment_id, and list is paginated. What is missing is guidance on when an agent should choose this tool over alternatives, and the default action (list) is not stated in prose even though the schema defaults it.

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