Skip to main content
Glama

Get system log

unifi_get_system_log
Read-only

Read paged UniFi v2 system log entries by alert class, including device, client, admin, update, threat, VPN, trigger, and AI alerts, with configurable lookback and page size.

Instructions

Read one class of the v2 system log (Network 8+), paged (default 50 entries from the last 168 hours): device-alert (default), client-alert, admin-activity (logins and config changes), update-alert, threat-alert (IPS/honeypot), vpn-alert, triggers (traffic/firewall rule hits) or next-ai-alert. Entries have time, key, category, severity, title, message, device and client. unifi_list_events reads the classic event log.

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": "unifi_get_system_log"
  }
}

Input Schema

NameRequiredDescriptionDefault
rawNoReturn raw entries
pageNoPage number, from 0
siteNoSite name/ID as used in the API (e.g. 'default'). Defaults to the configured site. See unifi_list_sites.
classNoLog class (default device-alert)
hoursNoLook back this many hours (default 168)
page_sizeNoEntries per page (default 50)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.8.1

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered; the description adds version gating (Network 8+), default time window, default paging, and the shape of returned entries (time, key, category, severity, title, message, device, client). It does not explain the idempotentHint=false annotation or any pagination termination behavior, which is the remaining gap.

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 core action and scope, then the class list, then the return shape, then the sibling disambiguation. Dense but nearly every clause carries information; the parenthetical glosses are compact rather than wasteful. Slightly packed into two long sentences, which costs it a point.

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?

No output schema exists, and the description compensates by listing the entry fields an agent will receive, plus version requirements and paging defaults. Combined with full schema coverage, an agent has enough to call this correctly; only the semantics of 'raw' and the meaning of the non-idempotent hint are left unexplained.

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 coverage is 100%, so the baseline is 3, but the description goes beyond the schema by glossing the enum values: admin-activity is 'logins and config changes', threat-alert is 'IPS/honeypot', triggers are 'traffic/firewall rule hits'. It also restates the hours and page_size defaults in prose. The 'raw' parameter remains unclarified beyond the schema's terse 'Return raw entries'.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource (read one class of the v2 system log), gives the version requirement (Network 8+), enumerates every available class, and explicitly names the sibling it is not: 'unifi_list_events reads the classic event log.' An agent can distinguish this from the event-log tool without opening either schema.

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?

Clear context for use: pick one log class, defaults to device-alert, default window of 168 hours, default page size 50. It also routes away from the classic event log by naming unifi_list_events. It stops short of explicit when-to-use/when-not conditions (e.g. which class answers which question), so it is not a full 5.

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