Skip to main content
Glama
Sentry MCP

Sentry MCP

Official
by getsentry

Get Agent Conversation Details

get_agent_conversation_details
Read-only

Retrieve a Sentry agent conversation transcript showing ordered user and assistant messages and tool calls with trace and span IDs for debugging. Use it to inspect one conversation after locating it by ID.

Instructions

Get the transcript of one Sentry agent conversation (formerly AI conversation): user and assistant messages and tool calls in order, with trace and span IDs for debugging. To find conversations, use search_agent_conversations.

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": {
      "conversationId": "<conversationId>"
    },
    "name": "get_agent_conversation_details"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNoEnd of the lookup window; requires start.
freshNoBypass cached reads.
startNoStart of the lookup window; requires end.
projectNoNumeric project ID to scope the lookup; omit to search all projects.
regionUrlNoThe organization's region URL from `find_organizations`, e.g. `https://us.sentry.io`. Omit for self-hosted Sentry.
conversationIdYesThe agent conversation ID from gen_ai.conversation.id.
organizationSlugNoThe organization slug, from `find_organizations`. In `org/project` notation, the part before the slash.

Output Schema

NameRequiredDescriptionDefault
urlYes
titleYes
projectsYes
timelineYes
traceIdsYes
spanCountYes
aiCallCountYes
totalTokensYes
endTimestampYes
lookupWindowYes
messageCountYes
spanSummariesYes
toolCallCountYes
conversationIdYes
startTimestampYes
organizationSlugYes

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 that results are ordered and carry trace/span IDs for debugging, but with an output schema present it does not need to explain the payload further, so this is incremental rather than rich context.

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?

Two sentences, front-loaded with the core action and payload, followed by the routing hint. Nothing is redundant and the sibling pointer is placed where an agent will act on it.

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 read-only lookup with an output schema and full parameter documentation, the description covers what the tool returns and how to discover valid IDs. Only edge behavior such as a missing or inaccessible conversation is unaddressed, which is a minor gap.

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 100%, so every parameter including the required conversationId, project scoping, start/end window pairing, and regionUrl is already documented. The description adds no format or constraint detail beyond the schema, so the baseline 3 applies.

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 ('Get the transcript of one Sentry agent conversation') and enumerates the contents (user/assistant messages, tool calls in order, trace and span IDs). The parenthetical 'formerly AI conversation' disambiguates naming, and the sibling it is not is stated explicitly.

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 discovery to search_agent_conversations, which is the correct alternative when the conversation ID is unknown. It does not spell out the precondition that a conversationId must already be held or what to do on a miss, leaving a small inference gap.

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