Skip to main content
Glama

revue_changes

Lists files changed in a repository view—uncommitted work, a specific commit, or a branch against its base—with status and added/deleted line counts.

Instructions

List the files changed in a view of the repo (uncommitted work, a commit, or a branch vs its base), with status and added/deleted line counts. Returns text to you; to show changes to the user, use revue_open or revue_show.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "revue_changes"
  }
}

Input Schema

NameRequiredDescriptionDefault
gitNofalse opens the folder as a plain folder (its files only, including .git) even inside a git repo, like revue --no-git. Default true.
refNoCommit to show in commit mode (default HEAD).
baseNoBase branch in branch mode (default: main, master, origin/main, origin/master or develop, whichever exists).
headNoBranch to view in commit/branch mode without checking it out (default: the checked-out branch).
modeNoworking = uncommitted changes vs HEAD (default); commit = one commit vs its parent; branch = head vs its merge-base with base, like a PR.
repoNoAny folder inside the git repo. Defaults to the current working directory. A folder outside any repo opens as a plain folder: its files only, with no changes, history or modes.
persistNoIf a server has to be started: true keeps it running after this agent session ends, false stops it with the session. Defaults to the --lifetime setting.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the safety burden, and it does disclose the non-obvious trait that output is raw text to the agent rather than a rendered view. It omits two relevant behaviors implied by the schema: that a server may be started (the persist parameter) and that large-change output may be unbounded or truncated.

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 sentences, both load-bearing: the first defines the operation and return payload, the second handles the display hand-off. The operation is front-loaded and there is no redundant restatement of the title.

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 7-parameter tool with no output schema, the description covers the operation, the three modes, and the return shape well enough to call correctly. The gaps are the unmentioned server-start side effect and output size behavior, which matter for a git listing but are secondary given the fully documented schema.

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 coverage is 100%, with detailed per-parameter text for git, ref, base, head, mode, repo, and persist, so the baseline is 3. The description adds no parameter-level meaning beyond restating the three modes at a high level ("uncommitted work, a commit, or a branch vs its base").

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?

States a specific verb and resource ("List the files changed in a view of the repo") and immediately enumerates the three scopes it covers: uncommitted work, a commit, branch vs base. It also states the payload shape (status plus added/deleted line counts), so an agent knows what it gets without opening the schema.

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?

Explicitly routes a distinct case elsewhere: "to show changes to the user, use revue_open or revue_show," making the text-vs-render split unambiguous. It does not state when-not conditions relative to closer siblings such as diff or status, but the mode enumeration inside the description already frames the intended use cases.

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