forgejo-mcp

Review pull request

create_pull_request_review

Submit a pull request review in Forgejo/Gitea with optional inline comments. Approve, request changes, or comment; omit event to leave it pending.

Instructions

Submit a review on a pull request, optionally with inline comments. Omit event to leave the review pending.

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": {
      "owner": "<owner>",
      "repo": "<repo>",
      "index": "<index>"
    },
    "name": "create_pull_request_review"
  }
}

Input Schema

Name	Required	Description
`body`	No
`repo`	Yes	Repository name
`event`	No
`index`	Yes	Pull request number
`owner`	Yes	Repository owner (user or organization)
`comments`	No
`commit_id`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 17, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already declare readOnly=false and destructive=false, so the safety profile is covered. The description adds a real behavioral trait beyond them: omitting `event` produces a pending review rather than a submitted one, which materially changes the outcome. It does not mention notifications or auth needs, but the pending-state disclosure is meaningful added value.

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 tight sentences, front-loaded with the core action and immediately followed by the key conditional. No filler or redundancy; every clause earns its place.

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 mutation tool with no output schema and 43% schema coverage, the definition is only partially complete. It omits the shape of inline comments, the effect of `commit_id`, and the consequences of each `event` value, so an agent still needs to infer how to construct a full review.

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 only 43%, so the description must compensate, and it partially does by explaining `event` semantics and the `comments` capability. But it never documents the inline-comment structure (path/body/new_position/old_position), `commit_id`, or the enum values' effects, leaving much of the parameter surface unexplained.

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 states a specific verb and resource ('Submit a review on a pull request') and clarifies the optional inline-comments capability. It is clearly distinct from siblings like list_pull_request_reviews or request_pull_request_reviewers, though it never names those alternatives explicitly, so it stops short of a top score.

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?

It gives one genuine usage rule ('Omit `event` to leave the review pending'), which is actionable. However, it never says when to use this tool versus updating a PR or requesting reviewers, nor how to choose between APPROVED/REQUEST_CHANGES/COMMENT, leaving most routing to inference.

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

Deploy Server