Skip to main content
Glama
Sentry MCP

Sentry MCP

Official
by getsentry

Find Metric Monitors

find_metric_monitors
Read-only

Locate Sentry metric monitors that alert when error counts, latency, logs, metrics, or crash rates cross thresholds. Returns monitor IDs, queries, and connected alert rules.

Instructions

Find Sentry Metric Monitors that alert when an error count, latency, log, metric, or crash rate crosses a threshold. Returns monitor IDs, queries, and connected Alerts. Cron jobs: find_monitors. URL checks: find_uptime_monitors. Notifications: alert rules.

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_metric_monitors"
  }
}

Input Schema

NameRequiredDescriptionDefault
freshNoBypass cached reads.
limitNo
queryNoMonitor search, such as a name or name:"latency". Matches monitor metadata, not the monitored event query.
cursorNoNext cursor from the previous page, with the same filters.
regionUrlNo
projectSlugNoThe project slug, or lowercase `all` for every project.
organizationSlugNoThe organization slug, from `find_organizations`. In `org/project` notation, the part before the slash.

Output Schema

NameRequiredDescriptionDefault
monitorsYes
nextCursorYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.0.1

TDQS

A4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true, so the safety profile is covered. The description adds a return summary (monitor IDs, queries, connected Alerts), but that overlaps with the existing output schema and adds little. Nothing is said about pagination limits, caching, or the fact that the query parameter matches metadata rather than the event query — that important caveat lives only in 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?

Three tight lines with no filler: purpose and threshold definition first, then sibling routing for the two confusable cases. Every sentence earns its place and the most disambiguating information is front-loaded.

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 seven-parameter read-only list tool with an output schema, the description covers what it returns and where to go for adjacent resource types. Pagination behavior and the metadata-vs-event-query caveat are left entirely to the schema, which is acceptable given the 71% coverage but not fully self-sufficient.

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?

Seven optional parameters with 71% schema description coverage, and the description documents none of them. The schema itself carries the non-obvious semantics (query matches monitor metadata, not the monitored event query; cursor must reuse the same filters; regionUrl from find_organizations), so the schema does the work and the description neither helps nor misleads.

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?

Names a specific verb and resource ('Find Sentry Metric Monitors') and goes further by defining what a metric monitor is — alerts on error count, latency, log, metric, or crash rate thresholds. That definition lets an agent distinguish this tool from find_monitors and find_uptime_monitors without opening either 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 three adjacent resource types away from this tool: cron jobs go to find_monitors, URL checks to find_uptime_monitors, and notification configuration to alert rules. No guidance on when to prefer get_metric_monitor_details or update/delete siblings for a known monitor, so the find-vs-get boundary is left implicit.

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