Skip to main content
Glama
Sign In

Atwork

by so.atwork
OverviewDiscussionsAdmin

Post Comment

comment.post

Post a comment on an item, named by its sheetId and item id (uuid). The comment is attributed to the agent (visible as 'AI commented'). The user can delete the comment from the item's activity log.

Input Schema

NameRequiredDescriptionDefault
itemIdYesThe item's id (uuid)
contentYes
sheetIdYesThe sheet the item is on

Output Schema

NameRequiredDescriptionDefault
messageIdYesId of the posted comment
conversationIdYesThe item conversation the comment was posted in

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changed
    • addedInput schema / properties / itemId / description
      Added value: +"The item's id (uuid)"
    • removedInput schema / properties / itemId / exclusiveMinimum
      Removed value: -0
    • addedInput schema / properties / itemId / format
      Added value: +"uuid"
    • removedInput schema / properties / itemId / maximum
      Removed value: -9007199254740991
    • addedInput schema / properties / itemId / pattern
      Added value: +"^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    • changedInput schema / properties / itemId / type
      Previous value: -"integer"New value: +"string"
    • addedInput schema / properties / sheetId
      Added value: +{
+  "description": "The sheet the item is on",
+  "exclusiveMinimum": 0,
+  "maximum": 9007199254740991,
+  "type": "integer"
+}
    • changedInput schema / required
      Previous value: -[
-  "itemId",
-  "content"
-]New value: +[
+  "sheetId",
+  "itemId",
+  "content"
+]
  2. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, idempotentHint=false and destructiveHint=false, but the description adds genuinely non-obvious behavior: the comment is attributed to the agent and displayed as 'AI commented', and the user can remove it from the activity log. It does not mention side effects such as notifying watchers/assignees or whether due-date/mention triggers fire, which would be the remaining gap.

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?

Three short sentences, front-loaded with the action and addressing scheme, then the two behavioral facts. The clause naming sheetId and item id duplicates schema text and could be trimmed, but nothing is padded.

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?

A mutation tool with only three required params, a supplied output schema, and annotations covering the safety profile; the description therefore only needs attribution/reversibility and addressing, which it covers. Notification behavior and content formatting are the notable omissions.

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 67%: sheetId and itemId are already documented in the schema, and the description largely restates that pair. It adds nothing about the undocumented `content` parameter (whether markdown or mentions are supported, the 5000-char limit), so it does not compensate for the coverage gap.

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 ('Post a comment on an item') plus the exact addressing scheme (sheetId + item uuid). No sibling tool posts comments, so there is no ambiguity to resolve; an agent can act on this immediately.

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?

Usage is implied rather than stated: it is clear this is the way to add a comment, but there is no guidance on when to comment versus using item.update_humanized or notifications, and no prerequisites (e.g. access requirements on the item).

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

All Atwork toolsInspect
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