Campos personalizados de um tipo de entidade (leads/contacts/companies/customers). Use os codes/ids retornados nos bodies de create/update.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | ||
| limit | No | ||
| account | No | ||
| entity_type | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare readOnly and idempotent behavior. The description does not contradict these and adds no additional behavioral information, which is acceptable given the low bar set by having annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence with no unnecessary words. It is well-structured and immediately conveys the tool's function.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description provides enough context for a simple list operation, including the entity types and a hint about the output (codes/ids). It does not elaborate on pagination or account handling, but these are optional and not critical for basic use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description implicitly explains the 'entity_type' parameter by listing valid values. However, it does not clarify the purpose of 'page', 'limit', or 'account' parameters. Since these are optional but present, the description partially covers parameter semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool deals with custom fields of an entity type (leads/contacts/companies/customers), and the name 'kommo_custom_fields' reinforces this purpose. It effectively distinguishes itself from other entity-specific tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides a usage hint: 'Use the codes/ids retornados nos bodies de create/update.' This tells the user how to apply the returned data. However, it does not explicitly state when to use this tool versus alternatives, though the specific focus on custom fields makes the context clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools follow a clear entity+action naming scheme, so leads_create, leads_get, etc. are easy to tell apart despite the repeated template in descriptions. Minor ambiguity exists between account and list_accounts, and the generic request tool may be confused with any specialized endpoint.
The dominant pattern kommo_<entity>_<action> is consistently used across most CRUD tools. Deviations like list_accounts, custom_fields, events, and request break the pattern but are still understandable and not chaotic.
48 tools is excessive for a CRM server, even with a large resource surface. Most of the count comes from flattened CRUD actions, which could have been consolidated into fewer, richer tools without losing clarity.
The toolset covers many core Kommo resources: leads, contacts, companies, customer, tasks, notes, pipelines, users, and conversations. However, deletes are missing for most entities, and several resources are read/list-only; the raw request tool fills some of these gaps but is not a first-class substitute.