Skip to main content
Glama
Sign In
doc-review

doc-review

by MichaelEight
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

review_open

Opens a folder or file in the doc-review web UI and returns its URL so users can read, edit, and comment on Markdown, text, or LaTeX files before sending feedback to the AI.

Instructions

Open a folder (or the folder of a file) in the doc-review web UI and return its URL. The user reads, edits and comments on .md/.txt/.tex files there, then presses "Send to AI". Put the returned url in a chat message before you call review_wait, which blocks for minutes and keeps anything said after it from reaching the user in time.

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": {
      "path": "<path>"
    },
    "name": "review_open"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYesAbsolute path of a folder, or of a file inside the folder to open.
open_browserNoOpen the URL in the default browser (default true).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.2/5.0
Behavior4/5

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

No annotations exist, so the description carries the full burden, and it does disclose the key behaviors: it opens a human-facing web UI, returns a URL, and the user must act inside it and press 'Send to AI' before the workflow can continue. It does not cover failure behavior (e.g. nonexistent path), session lifetime, or whether re-opening an already-open folder has side effects.

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?

Two sentences, front-loaded with what the tool does, followed by the operational constraint that matters most. No filler; the second sentence earns its length by encoding sequencing and the reason for it.

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?

With no output schema, the description correctly states the return value (URL) and describes the human-in-the-loop step needed to continue. For a two-parameter opener this is nearly complete; only error cases and session/repeat-open behavior are left unstated.

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 100%, so both parameters are already documented, and the description's 'folder, or of a file inside the folder' merely echoes the path description. It adds no new meaning for open_browser or path formats, 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 concrete verb and resource ('Open a folder... in the doc-review web UI'), covers the file-inside-folder variant, and names the return value (URL). This clearly separates it from review_wait, review_reply and the other review_* siblings, which operate on an already-open review session.

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?

It establishes sequencing explicitly: put the returned url in a chat message before calling review_wait, and explains why (review_wait blocks for minutes and delays anything said after it). That is strong when-to-use guidance relative to the most dangerous sibling, though it never explicitly states this is the entry point that must precede all other review_* calls, nor when not to use it.

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

Deploy Server

Other Tools