Skip to main content
Glama
Sentry MCP

Sentry MCP

Official
by getsentry

Create Cron Monitor

create_monitor

Set up a Sentry cron monitor to alert on missed, failed, or slow runs of a scheduled job. The job must send check-ins using the returned slug.

Instructions

Create a Sentry cron monitor that alerts on missed, failed, or slow runs of a scheduled job. Uptime URL checks: find_uptime_monitors. Metric thresholds: find_metric_monitors. The job must send check-ins with the returned slug (SDK monitor config or sentry monitor run). A disabled status you did not request means no cron seat was free: tell the user; it ignores check-ins until enabled. After an error or timeout, check find_monitors before retrying.

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": {
      "projectSlug": "<projectSlug>",
      "name": "<name>",
      "schedule": "<schedule>"
    },
    "name": "create_monitor"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesMonitor display name.
slugNoSlug that check-ins use. Derived from the name when omitted.
ownerNoOwner as `user:ID` or `team:ID`.
statusNoMonitor status. Disabled monitors ignore check-ins.
scheduleYesJob schedule: a crontab, or an interval such as every 15 minutes.
timezoneNotz database timezone for the schedule, e.g. `UTC`.
regionUrlNo
maxRuntimeNoMinutes a check-in may stay in progress before it fails.
projectSlugYesThe project slug. In `org/project` notation, the part after the slash.
workflowIdsNoAlert workflow IDs to connect, from find_alert_rules with `issue`.
checkInMarginNoMinutes after the expected time before a check-in counts as missed. Sentry treats 0 as 1.
organizationSlugNoThe organization slug, from `find_organizations`. In `org/project` notation, the part before the slash.
recoveryThresholdNoConsecutive successful check-ins before the issue resolves.
failureIssueThresholdNoConsecutive failed or missed check-ins before an issue opens.

Output Schema

NameRequiredDescriptionDefault
monitorYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.0.1

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only declare a non-read-only, non-destructive, open-world write; the description adds substantial context: the created monitor requires check-ins with the returned slug, a disabled status the caller did not request signals no free cron seat and the monitor will silently ignore check-ins, and retry behavior after errors needs a find_monitors check first. These are non-obvious operational traits an agent could not infer from the schema.

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?

Four compact sentences, none wasted. The core purpose and the sibling disambiguation come first, with the operational caveats following in descending order of importance.

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?

For a 14-parameter creation tool with an output schema and 93% schema coverage, the description supplies everything the structured fields cannot: the check-in contract, the cron-seat failure mode, and retry discipline. Return formatting is correctly omitted since an output schema exists.

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 description coverage is 93%, so the schema already documents all 14 parameters including schedule, status, thresholds, and regionUrl. The description's mention of "the returned slug" is consistent with the slug parameter but adds no semantics the schema does not already state.

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 Sentry cron monitor that alerts on missed, failed, or slow runs of a scheduled job." It immediately distinguishes this from the uptime and metric monitor variants by naming find_uptime_monitors and find_metric_monitors.

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?

Explicitly routes the agent: uptime URL checks go to find_uptime_monitors, metric thresholds to find_metric_monitors, and this tool for cron. It also gives recovery guidance (check find_monitors before retrying after an error or timeout) and an escalation path (tell the user when a disabled status appears unexpectedly).

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