ShadowGit MCP Server

Reply to a review comment

reply_to_review_comment

Posts a reply to a specific ShadowGit review comment by its ID, sharing what changed or answering the question; the comment stays open for the reviewer to resolve.

Instructions

Reply to one review comment the person sent from ShadowGit, by its id from get_review_comments: what you changed for it, or your answer to its question, in a sentence or two. ShadowGit shows the reply under the comment with your name and a snapshot: during a session, the one its next saved snapshot or its end makes, which holds your change; outside a session, the newest one as you reply. A reply leaves the comment open: only the person resolves it. Needs the ShadowGit app running.

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": {
      "id": "<id>",
      "text": "<text>"
    },
    "name": "reply_to_review_comment"
  }
}

Input Schema

Name	Required	Description
`id`	Yes	The comment's id, as get_review_comments gives it
`repo`	No	Project name or absolute path. Defaults to the current project.
`text`	Yes	What you changed for it, or your answer: at most 1,000 characters

Output Schema

Name	Required	Description	Default
`id`	Yes
`repo`	Yes
`reply`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Addedv2.9.0Nov 5, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Beyond annotations (which only declare non-read-only, non-destructive, non-idempotent, closed-world), the description discloses what the user sees (the reply under the comment attributed to you with a snapshot), which snapshot is attached in each session state, and that the comment's state is unchanged. It also states the runtime prerequisite ("Needs the ShadowGit app running"), which no structured field conveys.

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?

Front-loaded with the action and its input source, and every sentence is on-topic. The snapshot clause ("during a session, the one its next saved snapshot or its end makes, which holds your change") is dense and hard to parse, which costs it a point, but there is no filler.

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

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a small three-parameter mutation with an output schema and annotations already supplied, the description covers the remaining unknowns: where the id comes from, what the reply should say, what the user sees, snapshot attachment semantics, and the app-running prerequisite. An agent could call this correctly without further context.

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 documents id, text and repo, including the 1,000-character limit. The description only reinforces the id's provenance and adds loose length guidance ("a sentence or two"), and says nothing about the repo parameter's default. Baseline 3 applies when the schema carries the load.

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?

Specific verb + resource ("Reply to one review comment") with the exact source of the required id ("by its id from get_review_comments"), which also disambiguates it from the read-only sibling that lists comments. It further specifies what the reply body should contain ("what you changed for it, or your answer to its question").

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?

Clear context for use: reply per comment, with content guidance (one or two sentences describing the change or the answer), and an explicit workflow pointer that ids come from get_review_comments. It also sets a boundary expectation ("A reply leaves the comment open: only the person resolves it"), though it does not state outright when not to reply or offer an alternative action.

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

Deploy Server