Mark

Request Changes or Reject

review_post

Destructive

Sends a post back with decision: changes_requested plus a note, or rejects it (rejected, final). Needs the current rev. To approve, use approve_posts. On a channel set to admins only, only workspace admins can decide; anyone else is refused. A rejected post will not publish. Requesting changes unlocks the draft for editing. Rejecting a website post that sent a preview to its CMS deletes that preview draft when Mark may; otherwise cmsPreview says it is still in the CMS, where, and why, and so does the post's review note. Related: get_post, approve_posts, comment_on_post.

Input Schema

TableJSON Schema

Name	Required	Description
`rev`	Yes	Current rev from get_post.
`note`	Yes	What needs to change, or why it is rejected.
`postId`	Yes	Post id.
`decision`	Yes	changes_requested sends it back; rejected is final.

Output Schema

TableJSON Schema

Name	Required	Description
`appUrl`	Yes
`postId`	Yes
`decision`	Yes
`cmsPreview`	No	The post's preview draft in the website CMS: removed (Mark deleted it), or left_in_cms with its previewUrl and why (cannot_delete: Mark's API key may not delete it; edited: changed in the CMS; linked: a page that was in the CMS before Mark used it; live: a live page; unreachable: the CMS did not answer). Absent when the post had no preview.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 17, 2026

addedOutput schema / properties / cmsPreview

Added value: +{
+  "description": "The post's preview draft in the website CMS: removed (Mark deleted it), or left_in_cms with its previewUrl and why (cannot_delete: Mark's API key may not delete it; edited: changed in the CMS; linked: a page that was in the CMS before Mark used it; live: a live page; unreachable: the CMS did not answer). Absent when the post had no preview.",
+  "oneOf": [
+    {
+      "additionalProperties": false,
+      "properties": {
+        "outcome": {
+          "const": "removed",
+          "type": "string"
+        }
+      },
+      "required": [
+        "outcome"
+      ],
+      "type": "object"
+    },
+    {
+      "additionalProperties": false,
+      "properties": {
+        "outcome": {
+          "const": "left_in_cms",
+          "type": "string"
+        },
+        "previewUrl": {
+          "type": [
+            "string",
+            "null"
+          ]
+        },
+        "reason": {
+          "enum": [
+            "cannot_delete",
+            "edited",
+            "linked",
+            "live",
+            "unreachable"
+          ],
+          "type": "string"
+        }
+      },
+      "required": [
+        "outcome",
+        "previewUrl",
+        "reason"
+      ],
+      "type": "object"
+    }
+  ]
+}

First observedOct 1, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already flag destructiveHint=true and readOnlyHint=false, but the description goes well beyond them: rejected posts will not publish, changes_requested unlocks the draft for editing, and rejecting a CMS-previewed website post deletes the preview draft or reports why it cannot via cmsPreview. That is exactly the kind of destructive side-effect detail an agent needs.

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?

Front-loads the core action and the sibling routing in the first two sentences, and every sentence carries substance. The final CMS-preview sentence is dense and slightly convoluted, which keeps it from a 5.

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

Completeness5/5

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

Given an output schema exists, return values need not be explained, and the description still covers preconditions (current rev, admin-only channels), consequences of each decision, and related tools. Nothing needed to invoke it correctly is missing.

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 the schema already documents rev, note, postId and the decision enum. The description reinforces 'Needs the current rev' and the finality of 'rejected' but adds little syntax or format detail beyond the schema, so baseline 3 applies.

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 (sends a post back / rejects it) on a specific resource (post) with the two decision outcomes named. It explicitly distinguishes itself from the approve sibling, so an agent can route without opening schemas.

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

Usage Guidelines5/5

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

Explicitly says 'To approve, use approve_posts', giving the alternative and the condition that selects it. It also names the admin-only channel precondition and the refusal behavior for non-admins.

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

All Mark tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?