Skip to main content
Glama

revue_annotate

Leave an inline note on a code line or line range in the Revue diff and file view to explain a change, flag something for review, or ask a question about specific code.

Instructions

Leave a note on a line or line range, shown inline in revue under those lines (in the diff and the file view), and show it to the user. Use it to explain a change, flag something to review, or ask a question about specific code. Notes belong to the current view (mode/ref/base/head) and are marked outdated if the lines change later.

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": {
      "path": "<path>",
      "line": "<line>",
      "text": "<text>"
    },
    "name": "revue_annotate"
  }
}

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).
lineYesFirst line the note is about.
modeNoworking = uncommitted changes vs HEAD (default); commit = one commit vs its parent; branch = head vs its merge-base with base, like a PR.
pathYesFile path relative to the repo root.
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.
showNoAlso move the browser to the note (default true). Set false when leaving several notes, then call revue_show or revue_open once.
sideNonew (after the change, default) or old (before it, e.g. for deleted lines). Line numbers refer to this side.
textYesThe note. Plain text; newlines are kept.
authorNoShown on the note. Defaults to the MCP client's name.
newTabNoOpen a new browser tab even if a revue tab is already open.
endLineNoLast line, for a range.
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

A3.6/5.0
Behavior3/5

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

With no annotations, the description must carry the full behavioral burden, and it does disclose non-obvious traits: notes are scoped to the current view (mode/ref/base/head) and become marked outdated when lines change. It omits other side effects, however — that a server/browser may be started, that the browser view may move (default show=true), and that this is a write operation with no undo.

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?

Three sentences, front-loaded with the action and rendering location, then use cases, then view/staleness semantics. No sentence is filler, though the middle use-case sentence is somewhat expendable.

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

Completeness3/5

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

For a 15-parameter mutation tool with no annotations and no output schema, the description covers purpose, placement, and staleness but leaves gaps around server/browser side effects and what the call returns. An agent can call it, but it must read the schema to understand batching and session persistence.

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%, so all 15 parameters are already documented inline, establishing a baseline of 3. The prose adds framing for the view-scoping parameters (mode/ref/base/head) and for `show`, but adds no syntax, constraints, or defaults beyond what the schema states.

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?

The description opens with a specific verb and resource ("Leave a note on a line or line range") and states where the result appears (inline under those lines in the diff and file view). It is clearly distinguishable from read-oriented siblings like revue_annotations, though it never names a sibling explicitly.

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 concrete use cases — explain a change, flag something to review, ask a question about specific code — which tells an agent when this is the right tool. There are no explicit exclusions or named alternatives in the prose; the routing to revue_show/revue_open for batching only appears in the schema's `show` parameter.

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