Skip to main content
Glama
Sentry MCP

Sentry MCP

Official
by getsentry

Update Issue

update_issue
Destructive

Update a Sentry issue by resolving, ignoring, or reopening it, assigning it to a user or team, and changing its priority to match your triage workflow.

Instructions

Update a Sentry issue: resolve, ignore (archive), or reopen it, assign it to a user or team, or change its priority.

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": "update_issue"
  }
}

Input Schema

NameRequiredDescriptionDefault
reasonNoPosted as a comment on the issue's activity.
statusNoThe new issue status.
issueIdNoThe issue short ID, e.g. `PROJECT-1Z43`.
inCommitNoSHA of a commit Sentry knows that fixes the issue. Requires status `resolved` and inCommitRepository.
issueUrlNoThe issue URL, e.g. https://my-org.sentry.io/issues/PROJECT-1Z43
priorityNoThe new issue priority. Setting it stops Sentry from changing it automatically.
inReleaseNoFull version of the release that fixes the issue, exactly as find_releases returns it (e.g. `my-app@1.2.3+45`). Requires status `resolved`. Events from newer releases reopen it as a regression.
regionUrlNo
assignedToNo`user:<id>`, `team:<id>`, or `team:<slug>`. `null` unassigns. `whoami` returns your user ID.
ignoreModeNoWhen an ignored issue comes back. `untilEscalating` is the Sentry UI default. The `forDuration`, `untilOccurrenceCount`, and `untilUserCount` modes need their matching ignore fields.
ignoreCountNoOccurrences before the issue stops being ignored. Only with ignoreMode `untilOccurrenceCount`.
ignoreUserCountNoAffected users before the issue stops being ignored. Only with ignoreMode `untilUserCount`.
organizationSlugNoThe organization slug, from `find_organizations`. In `org/project` notation, the part before the slash.
inCommitRepositoryNoRepository of inCommit as Sentry names it, e.g. `getsentry/sentry`.
ignoreWindowMinutesNoWindow in minutes for ignoreCount. Omit to count all occurrences.
ignoreDurationMinutesNoMinutes to ignore the issue. Only with ignoreMode `forDuration`.
ignoreUserWindowMinutesNoWindow in minutes for ignoreUserCount. Omit to count all users.

Output Schema

NameRequiredDescriptionDefault
titleYes
effectYesWhat the new status means for the issue, when it changed.
changesYes
currentYes
issueIdYes
updatedYesWhether issue state changed. A posted reason comment is reported in reasonComment, not here.
issueUrlYes
sideQuestsNoOptional setup fixes and follow-ups, most useful first. Not needed for the current task.
reasonCommentYesNull when no reason was given.
organizationSlugYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.0.1

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is covered. The description adds a useful gloss that "ignore" means archive, but says nothing about reversibility, permission needs, or the coupling between resolve and release/commit info — that context 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?

One sentence, front-loaded with the verb and resource, followed by a tight colon-delimited list of the action families. No filler, no repetition of the title.

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?

For a 17-parameter destructive mutation with an output schema, the description is a reasonable high-level summary but omits meaningful behavior: the five ignore modes and their caveats, the resolve-with-release regression behavior, and the fact that assignment accepts user/team identifiers or null to unassign. The rich schema covers this, but an agent reading only the description would miss the complexity.

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 94%, so the schema carries nearly all parameter meaning, including ignoreMode variants and the inRelease/inCommit requirements. The description contributes a light grouping of actions but no additional syntax or constraint detail beyond what the schema states; baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb and resource ("Update a Sentry issue") and then enumerates the concrete action families: resolve, ignore/archive, reopen, assign to user or team, change priority. That is enough for an agent to distinguish it from read-only siblings like get_issue_details or add_issue_note, though it never names an alternative explicitly.

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?

Usage is implied by the enumerated actions rather than stated: an agent can infer this is the mutation tool for issue state, assignment, and priority. But there is no when-not guidance, no mention that at least one of issueId/issueUrl must be supplied, and no steering between this tool and siblings such as add_issue_note or link_issue.

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