Skip to main content
Glama
Zabbix MCP Server

Zabbix MCP Server

by mhajder

User Delete

user_delete
Destructive

Permanently remove user accounts from Zabbix, immediately revoking access while retaining historical data for audit purposes.

Instructions

Delete users from Zabbix.

Permanently removes user accounts from the system. The user's access will be immediately revoked. Historical data and previous actions by the user are retained for audit purposes.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "userids": "<userids>"
    },
    "name": "user_delete"
  }
}

Input Schema

NameRequiredDescriptionDefault
useridsYesUser IDs to delete.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.6.0
    • addedInput schema / properties / userids / minItems
      Added value: +1
  2. First observedv0.5.3

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is known; the description still adds real value by disclosing consequences — immediate access revocation and that historical data/audit trails survive the deletion. The only unaddressed trait is multi-ID behavior (all-or-nothing vs partial failure), which is relevant given the array parameter.

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

Conciseness5/5

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

Four short sentences, front-loaded with the action, then the permanence warning, then the audit-retention note. Nothing is repeated and no sentence is filler.

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 one-parameter destructive tool with full annotation coverage, a complete schema, and an output schema, the description covers purpose and consequences adequately. The missing piece is failure/partial-success behavior when several IDs are passed, which matters for a batch delete.

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 description coverage is 100% and the single 'userids' array is already documented as 'User IDs to delete', so the schema carries the burden. The description adds nothing about batch semantics or how multiple IDs are handled, so baseline 3 applies.

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 opens with a specific verb+resource ('Delete users from Zabbix') and elaborates that accounts are permanently removed, which clearly separates it from user_get, user_create, and user_update. It stops short of explicitly naming the non-destructive alternative (disabling via user_update), which is the one ambiguity an agent could face.

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?

Usage is implied rather than stated: 'Permanently removes' and 'access will be immediately revoked' telegraph that this is a last-resort operation, but there is no explicit when-to-use/when-not or pointer to siblings. An agent must infer that user_update is the reversible alternative.

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