Skip to main content
Glama

List anomalies

unifi_list_anomalies
Read-only

Lists controller-detected anomalies per client or device, such as high latency, DNS timeouts, and poor Wi-Fi experience, with a default lookback of 24 hours.

Instructions

List anomalies the controller detected per client or device (e.g. high latency, DNS timeouts, poor WiFi experience), default last 24 hours. Rows are returned as the controller reports them; not available on every Network version.

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_list_anomalies"
  }
}

Input Schema

NameRequiredDescriptionDefault
siteNoSite name/ID as used in the API (e.g. 'default'). Defaults to the configured site. See unifi_list_sites.
hoursNoLook back this many hours (default 24)
limitNoMaximum items to return (default 100)
fieldsNoOnly return these fields per item (dot paths, e.g. uplink.name)
searchNoCase-insensitive substring match on names, MACs, IPs and similar

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.9.1
    • addedInput schema / properties / fields / description
      Added value: +"Only return these fields per item (dot paths, e.g. uplink.name)"
    • changedInput schema / properties / limit / description
      Previous value: -"Default 100"New value: +"Maximum items to return (default 100)"
    • addedInput schema / properties / search / description
      Added value: +"Case-insensitive substring match on names, MACs, IPs and similar"
  2. First observedv0.8.1

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false), and the description adds two genuinely new behavioral facts: results are unnormalized ('Rows are returned as the controller reports them') and the endpoint may not exist on every Network version, warning the agent about possible failures. It stops short of saying how that unavailability manifests (error vs empty result), which keeps it below a 5.

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?

Two compact sentences, front-loaded with the resource and scope, followed by the behavioral caveats. 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?

With no output schema, the description does the necessary work of characterizing the returned rows and flagging version-dependent availability. It leaves open the pagination/limit behavior and what an unsupported version actually returns, which matters for a 5-parameter list 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 100%, so the five parameters are already fully documented; the description only restates the 24-hour default that the hours parameter already declares. The phrase 'per client or device' describes row granularity rather than a filter, and could momentarily suggest a client/device filter parameter that does not exist in the schema.

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?

States a specific verb and resource ('List anomalies the controller detected') and adds concrete examples of anomaly types (high latency, DNS timeouts, poor WiFi experience) plus the granularity ('per client or device'). It does not distinguish this from closely related siblings such as unifi_list_alarms or unifi_list_events, leaving the agent to infer the difference from names alone.

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?

Gives a default window ('last 24 hours') and an important availability caveat ('not available on every Network version'), which implies when the tool will fail. However, it never says when to prefer this over alarms or events, nor what to do when the endpoint is unsupported — usage is implied rather than prescribed.

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