Skip to main content
Glama
Sentry MCP

Sentry MCP

Official
by getsentry

Find Alert Rules

find_alert_rules
Read-only

Find Sentry issue alert rules and metric monitor alerts with their conditions, actions, owner, and environment to inspect notification workflows and monitor configurations.

Instructions

Find Sentry alert rules: Issue Alerts (notification workflows) and Metric Monitor alerts, with their conditions, actions, owner, and environment. Metric entries carry legacy IDs; find_metric_monitors returns canonical monitor IDs. Cron and uptime monitors: find_monitors, find_uptime_monitors.

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": "find_alert_rules"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoAlert family: `issue` for Alerts (workflows), `metric` for Metric Monitors.all
freshNoBypass cached reads.
limitNoMaximum rules per alert family.
queryNo
cursorNo
regionUrlNo
projectSlugNo
organizationSlugNoThe organization slug, from `find_organizations`. In `org/project` notation, the part before the slash.

Output Schema

NameRequiredDescriptionDefault
issueRulesYes
paginationYes
metricRulesYes
metricMonitorHintNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.0.1

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint and destructiveHint=false, so safety is covered. The description adds real behavioral context beyond that: metric entries carry legacy IDs, so results must be cross-referenced with find_metric_monitors, which is a data-quality caveat an agent could not infer from the annotations or schema. Pagination and cursor scoping are handled in the schema rather than the prose.

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?

Two tight sentences, front-loaded with the core purpose and followed by the sibling routing. The telegram-style fragment in the second sentence is efficient rather than confusing, and no sentence is wasted.

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 an output schema present, the description need not explain return shapes, and annotations cover the safety profile, so what remains is scoping and sibling routing, both delivered. Minor gap: no note on how the two alert families combine under kind=all or how limits behave per family, which the schema only hints at.

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 only 50% across 8 parameters, so the description carries some compensating burden; it does clarify the `kind` families in prose ('Issue Alerts (notification workflows) and Metric Monitor alerts'), reinforcing the enum. However it says nothing about limiting, querying, region URL, or the org/project slug pair, so half the parameters get no extra meaning here.

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 ('Find Sentry alert rules') and immediately scopes it to the two alert families it covers, listing what comes back (conditions, actions, owner, environment). The agent can tell it apart from create/update/get_alert_rule and from the monitor finders without opening a 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?

Explicitly routes away from this tool for other resource types: 'Cron and uptime monitors: find_monitors, find_uptime_monitors,' and the note about legacy metric IDs points to find_metric_monitors for canonical IDs. It does not discuss when to prefer this over get_alert_rule for a single rule, but the find-vs-get split is largely implied by the verb.

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