Skip to main content
Glama

cortex_open

Destructive

Opens an authorized URL in a shared or isolated browser session for Playwright automation, with optional observation and no automatic snapshot.

Instructions

Apri URL autorizzato nella sessione condivisa; nessuno snapshot automatico.

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": {
      "url": "<url>"
    },
    "name": "cortex_open"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYes
observeNo
sessionIdNoID restituito da newSession. Omettere per usare la sessione condivisa.
newSessionNoCrea una sessione isolata (massimo 4); incompatibile con sessionId.
project_pathNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0-dev.1

TDQS

C2.7/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, openWorldHint=true and non-idempotent, and the phrase 'nessuno snapshot automatico' usefully explains the practical consequence: nothing is captured automatically, so changes are not reversible via snapshot. That is real added context, but the description says nothing about the 4-session cap, authorization requirements, or what happens to the current page.

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?

A single short clause with no filler, and the scoping caveat ('no automatic snapshot') is placed where it is read immediately. It is efficient, though the brevity drifts toward under-specification rather than crispness.

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

Completeness2/5

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

For a destructive, open-world navigation tool with five parameters, 40% schema coverage, and no output schema, the description is too thin. It omits session-lifecycle behavior, the isolation option, and what the caller gets back, leaving the agent to infer call semantics from the schema alone.

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

Parameters2/5

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

Schema description coverage is only 40%, so the description needs to compensate and largely does not. It implies the shared-session default for sessionId and hints that the URL must be authorized, but observe, newSession, and project_path carry no explanation at all beyond the schema's own text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a concrete verb and resource ('Apri URL') and a target scope ('sessione condivisa'), so the basic action is identifiable. However, it frames the tool as only operating in the shared session even though the schema exposes newSession/sessionId for isolated sessions, and it offers no differentiation from siblings like cortex_run or cortex_peek.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no mention of alternatives such as cortex_run, and no stated prerequisites beyond the terse 'URL autorizzato'. An agent gets no signal about when this is the right call versus another browser-driving tool.

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