GitHub PR Issue Analyser

Overview Schema Source Related Servers Discussions Admin

Github Submit Review

github_submit_review

Submit a review (approve, request changes, or comment) on a specific pull request, optionally pinned to an exact commit SHA to ensure the reviewed code matches the submitted verdict.

Instructions

Submits a review for a specific pull request. GitHub applies a review to the newest commit unless told otherwise, so pass head_sha from github_get_pr_content as expected_head_sha to review the commit that was read. See #517.

Workflow and conventions: github_get_skill('pr-review').

Input Schema

Name	Required	Description
`body`	No
`event`	Yes
`pr_number`	Yes
`repo_name`	Yes
`repo_owner`	Yes
`expected_head_sha`	No	Attach the review to this SHA, as github_get_pr_content reports it. Omit for the newest commit

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv54.0.0Oct 24, 2026

addedInput schema / properties / expected_head_sha

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Attach the review to this SHA, as github_get_pr_content reports it. Omit for the newest commit"
+}

Addedv42.0.0Sep 15, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations only tell us it is a non-idempotent, non-destructive open-world write. The description adds genuinely non-obvious behavior: GitHub silently targets the newest commit unless a SHA is pinned, which is the classic stale-review hazard. It does not discuss permission requirements or what the response contains, but it earns credit for disclosing a real behavioral trap.

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?

Lead sentence states the action, second gives the practical SHA guidance, third routes to the skill. Efficient and front-loaded. The trailing 'See #517.' is an opaque dangling reference that costs a little clarity.

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?

Output schema exists, so return values need not be explained. But for a 6-parameter review-submission tool with three event modes, the description never says what each mode means or which fields each mode requires, leaving a meaningful gap for an agent choosing APPROVE vs REQUEST_CHANGES.

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 only 17%, so the description must compensate. It explains expected_head_sha well (though the schema already documents it) but gives no meaning for the event enum values (APPROVE / REQUEST_CHANGES / COMMENT) or the fact that body is effectively required for non-APPROVE events. Partial compensation only.

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?

Opens with a specific verb+resource: 'Submits a review for a specific pull request.' The use of 'review' rather than 'comment' implicitly separates it from github_add_pr_comments and github_add_inline_pr_comment, but no sibling is named explicitly, so differentiation requires inference.

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?

Gives a concrete procedural condition: pass head_sha from github_get_pr_content as expected_head_sha when you want the review attached to the commit you actually read, and points to github_get_skill('pr-review') for conventions. There is no explicit 'do not use this when...' guidance, so it stops short of a 5.

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

Deploy Server