phabricator-mcp

phabricator_revision_edit

Destructive

Modify a Differential revision to accept, reject, abandon, request review, plan changes, or commandeer it, and update reviewers, subscribers, comments, title, summary, or test plan.

Instructions

Edit a Differential revision. Supports actions like accept, reject, abandon, request-review, plan-changes, and commandeer. Can also add/remove reviewers, subscribers, and comments.

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": {
      "objectIdentifier": "<objectIdentifier>"
    },
    "name": "phabricator_revision_edit"
  }
}

Input Schema

Name	Required	Description
`draft`	No	Hold revision as draft (true) or release from draft (false)
`title`	No	New title
`action`	No	Revision action to take. Each action is sent as its own transaction type with value true.
`comment`	No	Add a comment
`summary`	No	New summary
`testPlan`	No	New test plan
`addTaskPHIDs`	No	Maniphest task PHIDs to associate
`addChildPHIDs`	No	Child revision PHIDs to add (dependents)
`addParentPHIDs`	No	Parent revision PHIDs to add (dependencies)
`repositoryPHID`	No	Repository PHID to associate with the revision
`addProjectPHIDs`	No	Add projects
`removeTaskPHIDs`	No	Maniphest task PHIDs to remove
`addReviewerPHIDs`	No	Add reviewers. Prefix with "blocking(PHID)" to add as blocking reviewer
`objectIdentifier`	Yes	Revision PHID or ID (e.g., "D123")
`removeChildPHIDs`	No	Child revision PHIDs to remove
`setReviewerPHIDs`	No	Replace all reviewers with this list. Prefix with "blocking(PHID)" for blocking
`removeParentPHIDs`	No	Parent revision PHIDs to remove
`addSubscriberPHIDs`	No	Subscriber PHIDs to add
`removeProjectPHIDs`	No	Remove projects
`removeReviewerPHIDs`	No	Remove reviewers
`removeSubscriberPHIDs`	No	Subscriber PHIDs to remove

Schema Changelog

Changes observed during successful MCP inspections.

First observedv2.0.19May 29, 2026

TDQS

B3.4/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the safety profile is covered. The description adds which field groups can be mutated, but says nothing about irreversibility, permission requirements, or the fact that the action list is partial ('like') — four enum values (reclaim, reopen, resign, close) are omitted from the prose.

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?

Two compact sentences, with the core purpose front-loaded and the capability summary following. Minor waste in the vague 'actions like' phrasing, which weakens precision without bloating the text.

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 21-parameter destructive mutation with no output schema, the description covers only a subset of the editable surface and omits any mention of irreversibility or result shape. The exhaustive schema compensates for parameter gaps, leaving behavior as the main shortfall.

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 the schema already explains all 21 parameters in detail. The description adds no format or semantics beyond what the schema states, and is silent on title/summary/testPlan/draft, projects, tasks, and revision dependency fields. 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?

Names a specific verb ('Edit') and resource ('Differential revision'), and the enumeration of actions makes the tool's scope concrete. It is clearly distinguishable from read-side siblings like phabricator_revision_search or phabricator_revision_inline_comment, though it never explicitly says so.

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?

The action list implies when the tool is used (to accept, abandon, request review, etc.), but there is no explicit guidance on when to prefer it over siblings such as phabricator_revision_inline_comment for line comments or phabricator_task_edit for task-side work. Usage is inferable rather than stated.

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

Deploy Server