Skip to main content
Glama
Sentry MCP

Sentry MCP

Official
by getsentry

Get Replay Details

get_replay_details
Read-only

Retrieve a Sentry session replay's summary and timeline of user actions, including page loads, clicks, inputs, console errors, failed requests, and feedback.

Instructions

Get a Sentry session replay's summary and a timeline of what the user did: page loads and navigations, clicks (including dead and rage clicks), inputs and key presses, console warnings and errors, failed requests, and feedback.

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": "get_replay_details"
  }
}

Input Schema

NameRequiredDescriptionDefault
skipNoMatching timeline events to skip; pass timeline.nextSkip from the previous response to see more.
freshNoBypass cached reads.
limitNoMaximum timeline events to return; defaults to 50.
replayIdNoThe replay ID, e.g. `7e07485f-12f9-416b-8b14-26260799b51f`.
regionUrlNo
replayUrlNoThe replay URL.
categoriesNoTimeline categories to show. Omit for notable events only; naming a category shows all its events, such as every request for network or every log level for console.
endOffsetSecondsNoWindow end, in seconds from the replay start; negative counts back from the end.
organizationSlugNoThe organization slug, from `find_organizations`. In `org/project` notation, the part before the slash.
startOffsetSecondsNoWindow start, in seconds from the replay start; negative counts back from the end, so -10 is the last 10 seconds.

Output Schema

NameRequiredDescriptionDefault
replayYes
relatedYes
timelineYes
suggestedActionsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.0.1

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already establish readOnly=true, destructive=false, openWorld=true, so safety is covered; the description's contribution is the returned content taxonomy, which is real but partly duplicative of the output schema. It says nothing about caching behavior (despite a `fresh` param), pagination continuation, or whether replays expire or require paid-plan access.

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?

A single front-loaded sentence with zero filler; the trailing list is not padding because each element tells the agent what evidence to expect. Nothing repeats the title or restates the name.

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, full annotations, and 90% schema coverage, the description carries only the burden of orienting the agent, and it does that well. The remaining shortfall is that with 10 optional params and no required ones, the description never clarifies the minimum identifying combination needed to make a successful call.

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 90%, so the schema already documents replayId, limits, offsets, and the categories enum; baseline is 3. The description adds nothing parameter-specific — no hint about which identifiers are needed together (replayId vs replayUrl, organizationSlug vs regionUrl) or how the default 'notable events only' behavior relates to the `categories` param.

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?

Specific verb+resource ("Get a Sentry session replay's summary and a timeline") followed by an explicit inventory of what the timeline contains: navigations, clicks including dead/rage clicks, inputs, console warnings/errors, failed requests, feedback. That enumeration makes it unmistakable against siblings like get_trace_details or get_issue_details, which surface different resources.

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

Usage Guidelines3/5

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

There is no explicit when-to-use/when-not guidance and no named alternative (e.g., trace vs replay debugging). Usage is implied by the resource name plus the fact that only replay IDs/URLs apply, but an agent must infer that this is the tool for 'what did the user actually do' investigation rather than being told.

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