Skip to main content
Glama
keycrm-mcp

keycrm-mcp

by IgorShutko

tasks

Manage KeyCRM to-dos: list, create, update, complete, delete, and retrieve by ID or linked lead, order, or client.

Instructions

Tasks (задачі). Creating a task really works on this account.

The API wants this body: name, priority, type, description, status, scheduled_at (ISO), assigned_to_id, tasked, attachments, period, checklist, settings.

actions: list - paginated tasks; tab="actual" (open) or "closed", mine=True only own tasks get - task by id for_entity - tasks attached to a card/order/client: entity_type (lead/order/client/task) + entity_id expired_count create - title, description, assigned_to_id, scheduled_at (ISO), priority, task_type; or pass data{} to override the whole body update - data{} with fields to change complete - mark as done (status=done) delete - DELETE /tasks/{id}

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": "tasks"
  }
}

Input Schema

NameRequiredDescriptionDefault
tabNoactual
dataNo
mineNo
pageNo
limitNo
titleNo
actionNolist
task_idNo
priorityNo
entity_idNo
task_typeNotask
descriptionNo
entity_typeNo
scheduled_atNo
assigned_to_idNo

Output Schema

NameRequiredDescriptionDefault
resultYes

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?

With no annotations at all, the description carries the full behavioral burden, and it partially meets it: it discloses that delete maps to DELETE /tasks/{id} (destructive), that complete sets status=done, and that list is paginated. It says nothing about permissions, whether delete is reversible, whether data{} override can silently wipe fields, or about rate limits, which are important for a mutation-capable tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The action list is well-structured and scannable with one line per operation. But the opening sentence is noise, and the body-field list under 'The API wants this body' is then partially repeated under create, spending words twice on the same information. Front-loading is decent but could be tightened considerably.

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 15-parameter multi-action tool with zero annotation coverage, the description gives a usable action-to-parameter map and an output schema exists so return values need not be explained. What is missing is the meaning of defaults (priority=1, task_type="task", page/limit semantics) and any warning about data{} replacing the whole body on update versus partial field changes.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 15 parameters, so the description must compensate, and it does map most parameters to specific actions: tab/mine to list, task_id to get, entity_type/entity_id to for_entity, and title/description/assigned_to_id/scheduled_at/priority/task_type to create, plus data{} as a full-body override. Gaps remain for page, limit, and the accepted enum values of entity_type, which are only loosely implied as lead/order/client/task.

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 names the resource (tasks) and enumerates concrete operations with specific targets: list, get, for_entity, expired_count, create, update, complete, delete. An agent can map an intent to an action without opening the schema. It does not contrast itself with sibling tools (leads, orders, clients), and the opening line about creation 'really working' is filler rather than scope.

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?

The action list implies when each operation applies (e.g. tab="actual" vs "closed", mine=True for own tasks, for_entity for card/order/client-attached tasks), which is real routing value. However, there is no explicit when-not guidance, no statement of prerequisites, and no mention of alternatives outside this tool. Usage must be inferred from the operation names.

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