phabricator-mcp

phabricator_transaction_comment_edit

Destructive

Edit a published Phabricator comment and save it as a new version using its transaction PHID and object identifier; does not apply to inline comments.

Instructions

Edit your own published comment (saves a new version). Not for inline 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>",
      "transactionPHID": "<transactionPHID>",
      "content": "<content>"
    },
    "name": "phabricator_transaction_comment_edit"
  }
}

Input Schema

Name	Required	Description
`content`	Yes	New text (Remarkup)
`transactionPHID`	Yes	The comment's PHID-XACT-… from phabricator_transaction_search
`objectIdentifier`	Yes	e.g. "T123", "D456", or a PHID

Schema Changelog

Changes observed during successful MCP inspections.

Addedv2.3.0Nov 5, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already flag readOnlyHint=false and destructiveHint=true; the description adds the important nuance that the edit 'saves a new version', so prior text is versioned rather than irrecoverably lost, and that the operation is limited to the caller's own published comments. It does not state what is returned or whether the comment must belong to a published (not draft) state beyond the word 'published'.

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 short clauses, front-loaded with the action and scope, with the exclusion placed after it. No filler or restatement of the tool name.

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 three-parameter, fully documented mutation tool with no output schema, the description covers purpose, ownership restriction, and the versioning behaviour that matters most to an agent. Slightly incomplete in not enumerating which comment surfaces it applies to or what happens to downstream notifications on edit.

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 each of the three required parameters carries its own explanation, including where to obtain transactionPHID. The description adds no parameter-level detail (e.g., Remarkup formatting caveats for 'content'), so the baseline of 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?

States a specific verb and resource ('Edit your own published comment') and immediately scopes it against a neighbouring capability ('Not for inline comments'), which maps onto siblings like phabricator_revision_inline_edit. It stops short of saying which object types this applies to (tasks, revisions, documents), leaving that to the schema examples.

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?

Gives a clear when-not ('Not for inline comments') and an implicit precondition via 'your own published' (you cannot edit other users' comments). It does not name the alternative tool explicitly, so the agent must infer that inline comments go to phabricator_revision_inline_edit / phabricator_revision_inline_publish.

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

Deploy Server