Skip to main content
Glama
Sentry MCP

Sentry MCP

Official
by getsentry

Analyze Issue with Seer

analyze_issue_with_seer

Run Seer AI root cause analysis on a Sentry issue to retrieve the root cause, affected code locations, and a suggested code fix.

Instructions

Run Seer AI root cause analysis on a Sentry issue and return the root cause, affected code locations, and a suggested code fix. Returns an existing analysis at once; a new one takes minutes, so call it only when the user asks for Seer or a fix, or the issue details do not show the cause. Does not support metric alert issues.

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": "analyze_issue_with_seer"
  }
}

Input Schema

NameRequiredDescriptionDefault
issueIdNoThe issue short ID, e.g. `PROJECT-1Z43`.
issueUrlNoThe issue URL, e.g. https://my-org.sentry.io/issues/PROJECT-1Z43
regionUrlNo
instructionNoExtra guidance for the analysis.
organizationSlugNoThe organization slug, from `find_organizations`. In `org/project` notation, the part before the slash.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.0.1

TDQS

A4.4/5.0
Behavior4/5

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

Adds real context beyond the annotations: a cached analysis returns immediately while a new analysis takes minutes, and metric alert issues are out of scope. The annotations declare openWorldHint and destructiveHint=false but do not convey that this triggers a slow server-side job, so the description earns credit here; it stops short of stating permission or rate-limit requirements.

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 sentences, front-loaded with capability and return values, then the latency tradeoff, then the use-condition and the exclusion. No filler and nothing repeated from the schema.

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 no output schema, the description correctly spells out what comes back and warns about the multi-minute wait. The only gap is that all five parameters are optional, yet the description never says which one is the minimum needed to launch an analysis.

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 80% and every parameter already carries its own description and examples, so the schema does the work. The description adds no syntax or format guidance for issueId, issueUrl, regionUrl, instruction, or organizationSlug, 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?

States a specific verb and resource ("Run Seer AI root cause analysis on a Sentry issue") and enumerates the return payload (root cause, affected code locations, suggested fix). That distinguishes it from plain issue-detail readers in the sibling list without needing to name them.

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?

Gives explicit selection criteria: use when the user asks for Seer or a fix, or when issue details do not show the cause, which implicitly routes to get_issue_details first. It also states an exclusion (metric alert issues unsupported) and a cost/latency condition that justifies deferring the call.

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