Skip to main content
Glama

Create Alertmanager silence

create_alertmanager_silence
Destructive

Create a silence in the cluster's Prometheus Alertmanager so matching alerts stop notifying (Slack, email, ...) until the silence ends. Matchers come from the alert's own labels - always anchor on an exact alertname matcher (e.g. alertname=KubeVersionMismatch) and add narrowing labels like cluster or namespace when known; at least one exact (non-regex) matcher is required. Duration accepts '30m', '2h', '24h', '14d', '2w' (default 2h, maximum 30d - longer suppressions need a human in Alertmanager/Grafana). A comment is required: it is the operator-visible reason shown next to the silence. The silence starts immediately (backdated one minute so it never sits pending) and the response carries the silence id - relay it so the silence can be expired early with expire_alertmanager_silence. The Alertmanager service is auto-discovered; pass namespace/service/port only for non-standard installs.

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": {
      "matchers": "<matchers>",
      "comment": "<comment>",
      "cluster_id": "<cluster_id>"
    },
    "name": "create_alertmanager_silence"
  }
}

Input Schema

NameRequiredDescriptionDefault
portNoAlertmanager port (default 9093).
commentYesRequired operator-visible reason, e.g. 'KubeVersionMismatch on ankra-production - silenced pending version alignment'.
serviceNoAlertmanager Service name override (requires namespace).
durationNoHow long the silence lasts: '30m', '2h', '24h', '14d', '2w'. Default 2h, maximum 30d.
matchersYesLabel matchers selecting the alerts to silence. Take them from the alert's labels; anchor on alertname.
namespaceNoNamespace to look for Alertmanager in (default: auto-discover across the cluster).
cluster_idYesAnkra cluster id (UUID) the call targets. Discover ids with list_clusters.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and idempotentHint=false, and the description adds real context beyond them: the silence starts immediately (backdated one minute so it never sits pending), the response carries the silence id, and Alertmanager is auto-discovered. It does not state what happens if the same silence is created twice, which is the main behavioral gap given idempotentHint=false.

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?

Purpose is front-loaded in the first clause, followed by constraints, duration rules, comment rationale, and return/relay guidance in a logical order. It is dense but nearly every sentence carries actionable information; the service/namespace/port sentence could be trimmed slightly given the schema already covers it.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite no output schema, the description tells the agent what the response contains (the silence id) and how to use it. Matcher requirements, duration bounds, required comment semantics, and auto-discovery behavior are all covered, leaving no material gap for correct invocation.

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 adds prescriptive meaning: anchor on an exact alertname matcher, add narrowing labels like cluster or namespace, accepted duration forms with default 2h and 30d cap, and that comment is the operator-visible reason. The namespace/service/port override guidance ('non-standard installs') also clarifies intent beyond the schema wording.

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?

Opens with a specific verb and resource ('Create a silence in the cluster's Prometheus Alertmanager') plus the concrete effect ('matching alerts stop notifying'). This clearly separates it from siblings such as create_alert or create_alert_destination, which create different object types.

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?

Gives explicit conditions: matchers must come from the alert's own labels, at least one exact matcher is required, and suppressions longer than 30d require a human in Alertmanager/Grafana. It also routes to expire_alertmanager_silence for early termination, though it does not contrast against list_alertmanager_silences or explain when a silence is the wrong tool versus muting elsewhere.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.