Skip to main content
Glama
Sentry MCP

Sentry MCP

Official
by getsentry

Update Alert Rule

update_alert_rule
Destructive

Modify an existing Sentry alert's name, status, owner, environment, frequency, triggers, notification actions, and connected projects or monitors while leaving omitted fields unchanged.

Instructions

Update a Sentry Alert (notification workflow): name, status, owner, environment, notification frequency, triggers, notification actions, and connected projects or monitors. Read it with get_alert_rule first; get_alert_options lists valid actions, conditions, and sources. Omitted fields stay unchanged. Metric Monitor queries and thresholds change with update_metric_monitor; cron and uptime monitors have their own tools.

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": {
      "ruleIdOrName": "<ruleIdOrName>"
    },
    "name": "update_alert_rule"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNo
ownerNoOwner as user:<id> or team:<id>. Null clears it.
statusNo
triggersNoComplete trigger group, copied from get_alert_rule. Keep existing condition IDs; omitted conditions are removed.
regionUrlNo
environmentNoEnvironment the Alert applies to. Null means all environments.
projectSlugNo
ruleIdOrNameYesAlert workflow ID from get_alert_rule, or exact Alert name. Digits are treated as an ID.
actionFiltersNoComplete list of action groups with their conditions and notification actions, copied from get_alert_rule. Keep IDs and unchanged entries; omitted groups, conditions, and actions are removed.
addDetectorIdsNoMonitor source IDs to connect, from get_alert_options sources. An all-project source also needs org:write.
addProjectSlugsNoProjects whose issue streams to connect.
frequencyMinutesNoMinimum interval between notifications, in minutes.
organizationSlugNoThe organization slug, from `find_organizations`. In `org/project` notation, the part before the slash.
removeDetectorIdsNoMonitor source IDs to disconnect.
removeProjectSlugsNoProjects whose issue streams to disconnect. Other monitors in those projects stay connected.

Output Schema

NameRequiredDescriptionDefault
alertRuleYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.0.1

TDQS

A4.3/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true and non-idempotent, so the safety profile is covered; the description adds the useful partial-update nuance that omitted fields stay unchanged. However, it never warns that the trigger and actionFilters structures are replaced wholesale (the schema says omitted conditions/actions are removed), which is the main destructive behavior an agent must know. That gap between 'omitted fields stay unchanged' and the nested replacement semantics is a real risk not surfaced in the description text.

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?

Three sentences, front-loaded with verb and resource, then prerequisites, then scope exclusions — a logical ordering. The field enumeration in sentence one largely restates schema properties and is slightly long, but it doubles as a usage hint about what can be changed.

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 15-parameter mutation tool with nested objects, the description supplies the read-before-write workflow, discovery tool for valid condition/action/source values, and sibling routing. With an output schema present there is no need to describe return values, and the remaining details (nested replacement semantics, org:write requirement for all-project sources) live in the schema.

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 description coverage is 73%, and the description adds meaning beyond it by mapping the enumerated mutable fields onto the parameter set and by pointing to get_alert_options as the source of valid values for triggers, notification actions, and detector IDs. It does not add format detail for parameters like ruleIdOrName or organizationSlug, but those are already documented in the schema.

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 ('Update a Sentry Alert (notification workflow)') and enumerates exactly which aspects are mutable: name, status, owner, environment, frequency, triggers, actions, and connected projects/monitors. It also explicitly separates itself from update_metric_monitor and the cron/uptime monitor tools, so an agent can pick it without opening schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives prerequisites and alternatives explicitly: read the rule with get_alert_rule first, use get_alert_options to discover valid actions, conditions, and sources, and use update_metric_monitor or the cron/uptime tools for those monitor types. It also states the partial-update rule ('Omitted fields stay unchanged'), which tells the agent what it need not resend.

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