atlassian-browser-mcp

Overview Schema Source Related Servers Discussions Admin

Update Issue

jira_update_issue

DestructiveIdempotent

Update an existing Jira issue by changing status, fields, assignee, description, components, attachments, or Epic links with its issue key.

Instructions

Update an existing Jira issue including changing status, adding Epic links, updating fields, etc.

Input Schema

Name	Required	Description	Default
`fields`	Yes	JSON string of fields to update. For 'assignee', provide a string identifier (email, name, or accountId). For 'description', provide text in Markdown format; on Jira Cloud, use '{expand:Title}...{expand}' for a collapsible section. Example: '{"assignee": "user@example.com", "summary": "New Summary", "description": "## Updated\nMarkdown text"}'
`issue_key`	Yes	Jira issue key (e.g., 'PROJ-123', 'ACV2-642')
`components`	No	(Optional) Comma-separated list of component names (e.g., 'Frontend,API')
`attachments`	No	(Optional) JSON string array or comma-separated list of file paths to attach to the issue. Example: '/path/to/file1.txt,/path/to/file2.txt' or ['/path/to/file1.txt','/path/to/file2.txt']
`return_fields`	No	(Optional) Controls which fields of the updated issue are returned, to reduce response size and token usage. Defaults to 'all' (the complete issue, which can be very large). TOKEN-SAVING TIP: after an update you usually do NOT need the whole issue back. Pass a comma-separated list of just the field(s) you care about (e.g., 'summary,duedate'), or a single light field such as 'status' for a minimal confirmation - this can cut the response by thousands of tokens. The issue 'key' is always returned regardless. If you later need other fields, fetch them on demand with jira_get_issue (which also supports field filtering). Use 'all' only when you genuinely need the full updated issue.	*all
`additional_fields`	No	(Optional) JSON string of additional fields to update. Use this for custom fields or more complex updates. Link to epic: {"epicKey": "EPIC-123"} or {"epic_link": "EPIC-123"}.

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedv1.4.1Nov 2, 2026

addedInput schema / additionalProperties
```
Added value: +false
```

changedInput schema / properties / fields / description

Previous value: -"JSON string of fields to update. For 'assignee', provide a string identifier (email, name, or accountId). For 'description', provide text in Markdown format. Example: '{\"assignee\": \"user@example.com\", \"summary\": \"New Summary\", \"description\": \"## Updated\\nMarkdown text\"}'"New value: +"JSON string of fields to update. For 'assignee', provide a string identifier (email, name, or accountId). For 'description', provide text in Markdown format; on Jira Cloud, use '{expand:Title}...{expand}' for a collapsible section. Example: '{\"assignee\": \"user@example.com\", \"summary\": \"New Summary\", \"description\": \"## Updated\\nMarkdown text\"}'"

changedInput schema / properties / issue_key / pattern

Previous value: -"^[A-Z][A-Z0-9_]+-\\d+$"New value: +"^[A-Z][A-Z0-9_]+-\\d+(?:-\\d+)*$"

addedInput schema / properties / return_fields

Added value: +{
+  "default": "*all",
+  "description": "(Optional) Controls which fields of the updated issue are returned, to reduce response size and token usage. Defaults to '*all' (the complete issue, which can be very large). TOKEN-SAVING TIP: after an update you usually do NOT need the whole issue back. Pass a comma-separated list of just the field(s) you care about (e.g., 'summary,duedate'), or a single light field such as 'status' for a minimal confirmation - this can cut the response by thousands of tokens. The issue 'key' is always returned regardless. If you later need other fields, fetch them on demand with jira_get_issue (which also supports field filtering). Use '*all' only when you genuinely need the full updated issue.",
+  "type": "string"
+}

removedOutput schema / description

Removed value: -"Generic wrapper for non-object return types."

Addedv1.0.1Apr 14, 2026

TDQS

C2.6/5.0

Behavior2/5

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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=true, so the risk profile is known from structured data. The description adds no behavioral context of its own — it does not say that unlisted fields are left untouched, whether status changes require a valid transition, or what permissions are needed, and 'etc.' actively obscures the mutation surface.

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?

One short sentence with no filler — appropriately sized. The only waste is the imprecise terminal 'etc.', which adds words without adding scope.

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

Completeness2/5

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, but this is a destructive, open-world mutation tool and the description gives no routing to the more specific sibling tools nor any note on partial-update semantics. For a 6-parameter mutation with this many overlapping siblings, the description is too thin.

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% and the field-level descriptions are unusually rich (assignee identifier formats, Markdown/expand syntax, the token-saving return_fields guidance), so the description is not required to compensate. It adds nothing beyond the schema, which is the baseline-3 case.

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

Purpose3/5

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

Names a specific verb and resource ('Update an existing Jira issue') and lists some capabilities, but the trailing 'etc.' leaves scope unbounded. It also claims 'changing status' as an in-scope action even though the sibling jira_transition_issue exists for exactly that, so it fails to distinguish itself from its closest alternative.

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

Usage Guidelines2/5

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

There is no statement of when to use this tool versus jira_transition_issue, jira_assign_issue, jira_link_to_epic, or jira_edit_comment, all of which are siblings that perform actions this description claims to cover. No prerequisites or exclusions are given.

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

Deploy Server