Mark

Comment on Post

comment_on_post

Adds a review comment to a post's current revision, visible to your team in Mark. To comment on part of the post, start the body with that text quoted, each line prefixed "> ", then a blank line, as Mark's chat preview does. Does not change the post's status. Related: get_post, review_post.

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": {
      "postId": "<postId>",
      "body": "<body>"
    },
    "name": "comment_on_post"
  }
}

Input Schema

Name	Required	Description	Default
`body`	Yes	The comment, under 5000 characters.
`postId`	Yes	Post id.

Output Schema

Name	Required	Description	Default
`appUrl`	Yes
`postId`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 1, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly=false, destructive=false, idempotent=false), so the bar is lower, yet the description still adds real behavior: the comment is scoped to the current revision, is team-visible, and does not mutate post status. It omits any note on failure cases or whether comments are editable, keeping it short of a 5.

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?

Three sentences, front-loaded with the action, then the one non-obvious formatting rule, then the boundary condition and siblings. No filler; the trailing phrase clarifying the quote style is short and functional.

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

Completeness4/5

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

Only two required params, both schema-documented, and an output schema exists so return values needn't be described. Annotations carry the safety profile. Slightly short of complete only because it says nothing about comment visibility permissions or behavior on a locked/unknown postId.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so body and postId are already documented; the description nonetheless adds a formatting contract for partial-post comments (quote with "> " prefix per line, then a blank line) that the schema does not express. That goes beyond baseline 3, though it does not clarify postId semantics.

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 and resource ("Adds a review comment to a post's current revision") plus the visibility scope ("visible to your team in Mark"). The note that it "does not change the post's status" separates it from review_post/approve_post siblings, so an agent can pick it without comparing schemas.

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?

Names related tools (get_post, review_post) but never states the condition that selects one over the other — no "use this when you want X instead of Y." The use case is implied by the verb rather than stated as guidance.

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?