Skip to main content
Glama
Sign In
annotate-mcp

annotate-mcp

by ElaineMHr
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

annotate_open

Open a persistent Chrome browser with an annotation toolbar on any page, optionally navigating to a URL, to enable marking up live sites. Call first to start an annotation session.

Instructions

Open the annotation browser (headed Chrome, persistent profile) and optionally navigate to a URL. The comment/pencil toolbar is injected into every page automatically. Call this first; the human then browses and marks up pages themselves. ALWAYS follow this with annotate_wait in the same turn — the human expects pressing Send to reach you, and it only does while something is parked.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "annotate_open"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlNoURL to navigate to, e.g. http://localhost:3003

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

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

With no annotations provided, the description carries the full burden. It discloses key behavioral traits: headed Chrome, persistent profile, automatic toolbar injection, optional URL navigation, and the requirement to follow with annotate_wait. It also explains the 'parked' mechanism, adding valuable context beyond the schema.

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?

The description is three tight sentences, front-loaded with the core action. The additional sentences explain the injected toolbar and the mandatory follow-up with annotate_wait, each earning its place. No fluff or redundancy.

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 the tool's nature (opening a browser for human interaction), the description covers the essential aspects: what it does, sequence constraints, and why the wait is necessary. It doesn't need to explain return values since there's no output schema. The description provides enough context for correct invocation.

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% for the single parameter 'url', so the schema already documents its meaning. The description only says 'optionally navigate to a URL', which adds no new information beyond what the schema provides. Baseline 3 is appropriate.

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?

The description clearly states the tool opens the annotation browser (headed Chrome, persistent profile) and optionally navigates to a URL. The verb 'Open' is specific, and the resource and behavior distinguish it from sibling tools like annotate_inbox or annotate_screenshot.

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?

Explicit guidance is given: 'Call this first' and 'ALWAYS follow this with annotate_wait in the same turn'. It explains why this ordering is necessary (human expects Send to reach you only while something is parked), providing clear when-to-use vs. alternatives.

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