Skip to main content
Glama
Sentry MCP

Sentry MCP

Official
by getsentry

Find Dropped Events

find_dropped_events
Read-only

Identify events Sentry dropped before storage—from sampling, filters, rate limits, or quotas—and compare dropped vs. accepted volume to explain missing or flat data.

Instructions

Find events Sentry dropped before storing them (SDK sampling, filters, rate limits, quota, spike protection), as dropped and accepted volume over time by outcome and reason. Each drop is tagged intentional (sampling, filters) or unintentional (quota, abuse). Use it to explain flat, low, or missing data that searches, charts, and dashboards cannot show; no drops means the data is complete.

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_dropped_events"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNo
freshNoBypass cached reads.
startNo
reasonNo
datasetNoData type to report drops for.spans
outcomeNo
intervalNo
regionUrlNo
projectSlugNo
statsPeriodNo
organizationSlugNoThe organization slug, from `find_organizations`. In `org/project` notation, the part before the slash.

Output Schema

NameRequiredDescriptionDefault
datasetYes
intervalYes
droppedEventsYes
acceptedEventsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.0.1

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already cover safety (readOnlyHint=true, destructiveHint=false, openWorldHint=true), and the description adds real context beyond them: drops are classified intentional (sampling, filters) vs unintentional (quota, abuse) and output is dropped and accepted volume over time by outcome and reason. It does not discuss the implications of the openWorldHint/regionUrl dependency or any rate limiting, but the interpretive framing is genuinely useful.

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 dense sentences with the identity of the tool stated first and interpretive guidance second; nothing is obviously padding. The parenthetical cause list and the intentional/unintentional clause are load-bearing, though the second sentence is long and could be split for faster scanning.

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

Completeness3/5

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

An output schema exists, so return values need not be explained, and the description covers purpose plus how to read the results. However, for an 11-parameter tool with thin schema coverage, missing scoping and time-range selection guidance leaves a real gap an agent would hit when actually invoking it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 11 parameters and schema description coverage reported at 27%, the description must carry the load but offers no guidance on scoping — nothing about organizationSlug/projectSlug requirements, regionUrl selection, choosing between statsPeriod and start/end, dataset defaults (spans), or interval limits. The only parameter-adjacent content is the phrase 'by outcome and reason,' which merely echoes the outcome/reason fields.

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 events Sentry dropped before storing them') and enumerates the causes (SDK sampling, filters, rate limits, quota, spike protection), so the agent knows this is a drop-accounting tool rather than an event search. It also implicitly separates itself from search/chart/dashboard siblings by stating they cannot show this data.

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 an explicit trigger: 'Use it to explain flat, low, or missing data that searches, charts, and dashboards cannot show,' plus a strong negative signal that 'no drops means the data is complete.' It does not name a specific alternative tool to use instead when the question is not about drops, so it stops short of full when/when-not routing.

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