Skip to main content
Glama
klarluft

GitWarren

by klarluft
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

List review comments

list_review_comments
Read-only

Retrieve every discussion on a review—line comments and threads—with full message history, anchors, and attachments. Use anchors to verify whether code has moved, is unchanged, or outdated before acting.

Instructions

Every discussion on a review: review-level threads and line comments alike, each with its full message history and who wrote each message. Line threads also carry an anchor saying where they land in the code as it stands right now - "anchored" (the line is unchanged), "moved" (the code shifted and anchor.line is its current line) or "outdated" (the line is gone, so the comment may be about code that has since been rewritten). Threads about files the diff does not contain are resolved against those files at the head rather than against the patch, so a comment on unchanged code reports an honest anchor too. Check the anchor before acting on a line comment. An outdated one still carries anchorSnapshot, the code as it read when the comment was written, which is how to tell what was being objected to before it was rewritten.

A body may contain images, written as markdown pointing at a gitwarren://attachment/... URL - that is an internal token, not something to fetch. Each one is resolved in the comment's attachments array, where path is a real file on disk: read it with your own image tools. alt is the description whoever attached it wrote, and is worth reading first - it is often enough on its own, and it is all you get if you cannot see images.

Each result carries guiUrl, a link that opens this in GitWarren. Show it to the user - it exists to be clicked, and it is how they see this without going and finding it themselves. The link works whether or not GitWarren is running right now, so hand it over without checking anything. If the user says it will not open - the browser reports that the connection was refused - then GitWarren is not running on their machine, and starting it makes the same link work. When the page is served by gitwarren serve or by a plugin rather than by the app, the link also carries that launch's token, which the page exchanges for a cookie; a link minted before a restart says it needs a token, and the newest link is the one that works.

When this machine is reachable on the user's tailnet, results also carry webUrl. The two links are for two situations and neither replaces the other: guiUrl opens GitWarren on the machine the user is sitting at, which is the right one when that is this machine; webUrl opens the same review in a browser from any of their devices - a phone, a laptop across the room - because it names this machine on their tailnet. Offer webUrl when the user is not at this machine, and both when you do not know.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
reviewIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.17

TDQS

A4.5/5.0
Behavior4/5

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

Annotations declare readOnlyHint=true and openWorldHint=false, so the safety profile is already known. The description adds substantial behavioral context: anchor semantics (anchored/moved/outdated), resolution of threads against head files rather than the patch, attachment URL behavior (internal token, not fetchable), guiUrl behavior across restarts and serve modes, and webUrl tailnet behavior. The only minor gap is that it doesn't explicitly state the return format or pagination, but the description is rich enough that this is a small omission.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is information-dense and front-loaded with the core purpose, but it is quite long and covers a lot of edge-case behavior (tailnet, tokens, cookies, restart behavior) that could be trimmed or moved to a more structured format. Every sentence does earn its place in terms of unique information, but the length makes it harder to parse quickly. It is not bloated with repetition, but it is at the upper limit of what an agent can efficiently consume.

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 read-only list tool with one parameter and no output schema, the description is remarkably complete. It covers the full range of what an agent needs to know: what results contain, how to interpret anchors, how to handle attachments, how to present links, and how to troubleshoot link failures. The absence of an output schema makes the description's detailed explanation of result fields (anchor, anchorSnapshot, attachments, guiUrl, webUrl) essential, and it delivers.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden for the single parameter. The description doesn't explicitly explain reviewId, but the tool name and title ('List review comments') plus the opening sentence make it clear that reviewId identifies the review whose comments are listed. With only one parameter and a self-evident name, the description's implicit coverage is adequate, though it could have explicitly stated 'reviewId: the review to list comments for.'

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?

The description opens with a clear statement of what the tool does: lists every discussion on a review, including review-level threads and line comments, with full message history and authorship. It distinguishes itself from sibling comment tools (add, reply, resolve, update, delete) by being the read/list operation, and from list_reviews by operating on comments within a review. The scope is specific and unambiguous.

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

Usage Guidelines5/5

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

The description provides extensive usage guidance: check the anchor before acting on a line comment, use anchorSnapshot for outdated comments, read the alt text before fetching attachments, show guiUrl to the user, offer webUrl when the user is not at this machine, and both when uncertain. It also explains when not to fetch attachment URLs and how to handle a link that won't open. This is explicit when-to-use and how-to-use guidance that goes far beyond a basic description.

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

Deploy Server

Other Tools