Skip to main content
Glama
klarluft

GitWarren

by klarluft
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Create review

create_review

Create a code review comparing two git refs, including uncommitted work on the checked-out branch, and return a clickable GUI link for feedback.

Instructions

Open a review comparing two refs in a tracked repository. baseRef is what the changes are measured against (usually the trunk) and headRef is the branch under review; the diff is taken from their merge base, like a pull request. Both refs must exist and share history, or the call fails with INVALID_INPUT. title defaults to " into ". If the head branch is checked out in a worktree, its uncommitted changes are part of the review as well - a review can be opened on work that has never been committed. Passing the same ref as both endpoints is allowed and does exactly that: the review then holds only the uncommitted work on that ref, and its title defaults to "Uncommitted work on ".

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
titleNo
baseRefYes
headRefYes
descriptionNo
repositoryIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.17

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only indicate a non-read, non-idempotent, non-destructive operation. The description goes far beyond that: it specifies the INVALID_INPUT failure mode, inclusion of uncommitted changes, URL behavior across server states and restarts, and token/cookie exchange. This is exactly the kind of behavioral context an agent needs and is not in annotations.

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?

The description is long but each sentence carries unique value. It is front-loaded with the core action and then layers ref semantics, output behavior, and URL usage. It could be trimmed slightly without losing meaning, but the structure is logical and not redundant.

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?

Given there is no output schema, the description explains the return values (guiUrl, webUrl) and their intended use, error handling, and edge cases (uncommitted work, same ref, server not running). This is complete for an agent to invoke the tool correctly and present results appropriately.

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

Parameters5/5

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

Schema description coverage is 0%, so the description must carry the parameter meaning. It thoroughly explains baseRef and headRef (including merge-base, uncommitted work, same-ref case) and the title default, and also covers description implicitly by allowing it. This fully compensates for the missing schema documentation.

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, specific verb+resource: 'Open a review comparing two refs in a tracked repository.' It distinguishes this creation tool from sibling review tools (list, get, update, remove) by explaining the diff-from-merge-base semantics, so an agent can select it without ambiguity.

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?

It gives practical conditions for use (both refs must exist, title default, same-ref allowed for uncommitted work) and explains when to offer guiUrl vs webUrl based on user context. It doesn't explicitly contrast with alternatives, but the purpose is unambiguous and the guidance is rich enough for correct invocation.

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