Skip to main content
Glama

Open a pull request review

start_review

Open a GitHub-style review page for uncommitted changes, commits, branches, or pull requests to collect inline comments, screenshots, and definition links, then return the review URL and ID.

Instructions

Opens a GitHub-style review page in the browser for uncommitted changes, commits on a branch, specific commits, or a whole branch. Shows a syntax-highlighted diff with inline (multi-line) comments, pasted screenshots, go-to-definition links and a per-file viewer. Returns the URL and a reviewId.

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": {
      "mode": "<mode>"
    },
    "name": "start_review"
  }
}

Input Schema

NameRequiredDescriptionDefault
prNoFor mode=pr: the pull request number. Omit to use the PR of the current branch.
baseNoBase ref for branch/range/all, e.g. origin/dev.
headNoHead ref for branch/range. Defaults to HEAD.
hostNoBind address. Default 127.0.0.1.
modeYesScope: uncommitted = working tree; branch = commits vs base; commits = explicit list; range = base..head; all = every commit on the branch; pr = a GitHub pull request read through the GitHub CLI.
portNoFixed port; 0 picks a free one.
titleNoOptional title in the page header.
branchNoBranch name shown in the UI (defaults to the checked-out branch).
prRepoNoFor mode=pr: owner/repo when the PR lives in another repository than the checkout.
commitsNoCommit SHAs/refs for mode=commits.
symbolsNoBuild the go-to-definition index. Default true.
repoPathNoRepository path. Defaults to the current working directory.
sessionIdNoOpenCode session that owns the review. Submit sends the fix turn to this session. Defaults to the session the server inherited.
includeStagedNoInclude staged changes (uncommitted). Default true.
includeUntrackedNoInclude untracked files (uncommitted). Default true.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations at all, the description carries the full burden; it does disclose that a browser page is opened and that a URL and reviewId are returned, which is genuinely useful. It omits the important behavioral facts: that a local HTTP server is presumably started and on what lifetime (the port/host params imply this but it is never said), whether the call is blocking, that pr mode shells out to the GitHub CLI, and that the review must later be closed.

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?

Two sentences, no filler, front-loaded with the verb and the set of supported scopes; the second sentence cleanly lists the UI capabilities and return values. The feature list ('syntax-highlighted diff with inline comments, screenshots, go-to-definition links, per-file viewer') is slightly promotional but still informative.

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, side-effecting tool with zero annotations and no output schema, the description covers what the tool does and what it returns but not the lifecycle (server binding, blocking behavior, how/when to close the review) or environment prerequisites. An agent could invoke it with a plausible mode but would be guessing about resource cleanup and failure modes.

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% across all 15 parameters, so mode, base/head, commits, port, sessionId and the include* flags are already fully documented in the schema. The description adds no syntax, defaults, or interaction rules between parameters beyond what the schema states, so the baseline of 3 applies.

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?

States a specific verb and resource ('Opens a GitHub-style review page in the browser') and enumerates the scopes it covers (uncommitted changes, branch commits, specific commits, whole branch), which lets an agent separate it from read-only siblings like get_review or list_review_scope. It stops short of naming an alternative tool outright, so differentiation is inferred from the verb rather than stated.

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

Usage Guidelines3/5

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

The enumeration of review scopes implicitly tells the agent when this tool applies, and the schema mode descriptions carry the per-mode selection logic. There is no explicit statement of when NOT to use it, no mention of the relationship to await_review/close_review (e.g. that a review is then awaited or closed), and no prerequisites such as needing a git checkout or the GitHub CLI.

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