Skip to main content
Glama
Sign In

Dockito

by ai.dockito
OverviewDiscussionsAdmin

Comment on a doc

comment

Start a comment thread, reply in one, resolve or reopen it, as the user (they need Comment or Edit on the doc; the token needs Publish or Everything). A new thread goes on the doc as a whole, or on a Markdown "quote" (the exact text as get shows it, with "before" to pick between repeats), a slide's "box" (s3.b2) or "slide" (s3), or a board's "item" (s4). "@Name" (or "@First" when only one person has it) in the text mentions someone who sees the comments; they and the thread's people are told in the app. Comments are edited and deleted in the Dockito app, not here.

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": {
      "doc": "<doc>",
      "action": "<action>"
    },
    "name": "comment"
  }
}

Input Schema

NameRequiredDescriptionDefault
boxNostart on Slides: the box's ID (s3.b2).
docYesThe doc's link or its code; a comment link names its thread too.
itemNostart on a board: the item's short ID (s4, k2, f1).
textNostart, reply: what to say. Plain text; @Name mentions.
quoteNostart on Markdown: the exact text the thread is on.
slideNostart on Slides: a slide as a whole (s3).
actionYesstart a thread, reply in one, resolve it or reopen it.
beforeNoWith quote: some text just before it, when the quote is in the doc more than once.
threadNoreply, resolve, reopen: the thread's ID (cth_…), unless the doc is a comment link.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the annotations (which only say non-read-only and non-destructive), the description discloses required permission pairs, the side effect that mentioned users and the thread's people are notified in the app, and the fact that threads are anchored to a doc, quote, slide, box, or board item. These are behaviors an agent cannot infer from the schema or annotations.

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?

Dense but front-loaded: actions first, permissions second, anchoring rules third, exclusions last. The heavy use of scare quotes around quote/before/box/slide/item makes parsing slightly slower, but no sentence is padding.

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?

For a 9-parameter, multi-surface mutation tool with no output schema, the description covers permissions, anchoring per surface, notification side effects, and out-of-scope operations. The notable gap is that it never says what comes back from start or reply — an agent needs the resulting thread ID to chain into reply/resolve/reopen.

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 the baseline would be 3, but the description adds real semantics: the quote must be the exact text as get shows it, before disambiguates repeated quotes, and thread is only needed when the doc is not itself a comment link. It also ties @Name mentions to text. It stops short of explaining how thread IDs are obtained after start.

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?

Opens with a specific verb set mapped to the resource: start a thread, reply, resolve, reopen. It is immediately distinguishable from edit_doc/edit_slides siblings because it only manages comment threads, and it explicitly states the acting identity ('as the user').

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 clear usage conditions: the user needs Comment or Edit on the doc, the token needs Publish or Everything. It also sets a boundary by saying comments are edited and deleted in the Dockito app, not here, which implicitly tells the agent not to look for those actions. It does not name a sibling tool for the excluded operations, so it falls short of full alternative routing.

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

All Dockito 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