Eric's Documentation Accuracy Review (#553)

* Update quickstart guides

* Update 'Create MCP server' and 'create auth tool'

* Self review

* Update 'tool with secrets' page

* Update Tools and Context

* Remove logging mcp tool activity

* Update url

* Update organize MCP server tools

* Update deploy docs

* Update evals

* Update cli page

* Address nit

* Address Mateos's comment & apply in multiple places

Author: EricGustin

app/en/home/api-keys/page.mdx

@@ -61,13 +61,17 @@ Visit the [API Keys page](https://api.arcade.dev/dashboard/api-keys) in Arcade D
 <Tabs.Tab>
 
 ```bash
-uv pip install arcade-ai
+uv tool install arcade-mcp
 ```
 
+<Callout type="info">
+This will install the Arcade CLI as a [uv tool](https://docs.astral.sh/uv/guides/tools/#installing-tools), making it available system wide.
+</Callout>
+
 </Tabs.Tab>
 <Tabs.Tab>
 ```bash
-pip install arcade-ai
+pip install arcade-mcp
 ```
 </Tabs.Tab>
 </Tabs>

app/en/home/arcade-cli/page.mdx

@@ -3,50 +3,36 @@ title: "Arcade CLI"
 description: "Learn how to install and use the Arcade CLI"
 ---
 
-import { Tabs } from "nextra/components";
+import { Tabs, Callout } from "nextra/components";
 
 # The Arcade CLI
 
-The Arcade CLI is a command-line tool that allows you to manage your Arcade deployments, generate, test, and manage your toolkits, and more.
+The Arcade CLI is a command-line tool that allows you to manage your Arcade deployments, generate, test, and manage your MCP servers, and more.
 
-This same package contains the SDK that you will use to [build your own toolkits](/home/build-tools/create-a-mcp-server).
+## Install the Arcade CLI
 
-## Installation
+In your terminal, run the following command to install the `arcade-mcp` package - Arcade's CLI:
 
-Like all python packages, the Arcade CLI needs to be installed within the python virtual environment you are using for your Arcade development environment.
-
-<Tabs items={["Python + uv", "Python + Conda", "Standard Python"]}>
-<Tabs.Tab>
-```bash
-# install uv: https://docs.astral.sh/uv/getting-started/installation/
+<Tabs items={["uv", "pip"]}>
+  <Tabs.Tab>
 
-uv venv --seed
-source .venv/bin/activate
+  ```bash
+  uv tool install arcade-mcp
+  ```
 
-````
-</Tabs.Tab>
-<Tabs.Tab>
-```bash
-# install miniconda: https://www.anaconda.com/docs/getting-started/miniconda/install
+  <Callout type="info">
+  This will install the Arcade CLI as a [uv tool](https://docs.astral.sh/uv/guides/tools/#installing-tools), making it available system wide.
+  </Callout>
 
-conda create --name arcade
-conda activate arcade
-````
+  </Tabs.Tab>
 
-</Tabs.Tab>
-<Tabs.Tab>
-```bash
-python -m venv .venv
-source .venv/bin/activate
-```
-</Tabs.Tab>
-</Tabs>
+  <Tabs.Tab>
 
-Now that your python virtual environment is activated, you can install the Arcade CLI with the following command:
+  ```bash
+  pip install arcade-mcp
+  ```
 
-<Tabs items={["uv", "pip"]}>
-  <Tabs.Tab>```bash uv pip install arcade-mcp ```</Tabs.Tab>
-  <Tabs.Tab>```bash pip install arcade-mcp ```</Tabs.Tab>
+  </Tabs.Tab>
 </Tabs>
 
 ## Usage

app/en/home/build-tools/_meta.tsx

@@ -1,9 +1,8 @@
 export default {
   "create-a-mcp-server": "Create an MCP Server",
-  "tool-context": "Tools and Context",
   "create-a-tool-with-auth": "Create a tool with auth",
   "create-a-tool-with-secrets": "Create a tool with secrets",
-  "logging-mcp-tool-activity": "Logging tool activity",
+  "tool-context": "Tools and Context",
   "organize-mcp-server-tools": "Organize MCP server tools",
   "providing-useful-tool-errors": "Providing useful tool errors",
   "retry-tools-with-improved-prompt": "Retry tools with improved prompt",

app/en/home/build-tools/call-tools-from-mcp-clients/page.mdx

@@ -84,18 +84,20 @@ You can customize a lot of the configuration passing options to `arcade configur
   </Tabs.Tab>
   <Tabs.Tab>
 
-Claude Desktop does not currently support the http transport.
+<Callout type="warning">
+Claude Desktop does not currently support the HTTP transport via JSON configuration files.
+</Callout>
 
   </Tabs.Tab>
 </Tabs>
 
 ### stdio specific configuration
 
-If you are using the stdio transport, `arcade configure` will assume the entrypoint (the script that contains the `MCPApp` instance and calls `app.run()`) to your MCP server is `server.py` and will set the working directory to the path of your entrypoint file. You can override this with the `--entrypoint` (or `-e`) option:
+If you are using the stdio transport, `arcade configure` will assume the entrypoint file (the script that contains the `MCPApp` instance and calls `app.run()`) to your MCP server is `server.py` and will set the working directory to the path of your entrypoint file. You can override this with the `--entrypoint` (or `-e`) option:
 
 <Callout type="info">
-  Note that the `--entrypoint` determines only the filename of the entrypoint
-  script, not the path to the script.
+  Note that the `--entrypoint` accepts only the filename of the entrypoint
+  file, not the path to the script.
 </Callout>
 <Callout type="info">
   When using the stdio transport, `arcade configure` will automatically load the
@@ -130,7 +132,7 @@ If you are using the stdio transport, `arcade configure` will assume the entrypo
   </Tabs.Tab>
 </Tabs>
 
-### http specific configuration
+### HTTP specific configuration
 
 If you are using the streamable HTTP transport, `arcade configure` will assume the MCP server is running on the default port `8000` and that the MCP server is running locally (in localhost). You can override this with the `--host` (or `-h`) and `--port` (or `-p`) options:
 
@@ -170,7 +172,9 @@ If you are using the streamable HTTP transport, `arcade configure` will assume t
   </Tabs.Tab>
   <Tabs.Tab>
 
-Claude Desktop does not currently support the http transport via JSON configuration files.
+<Callout type="warning">
+Claude Desktop does not currently support the HTTP transport via JSON configuration files.
+</Callout>
 
   </Tabs.Tab>
 </Tabs>
@@ -246,7 +250,7 @@ Each MCP client has a different way of configuring MCP servers. This section cov
 >
 <Tabs.Tab>
 
-When configuring your MCP client using the stdio transport, you need to ensure that the MCP server is called using the right version of python and within the correct working directory. For example, let's pretend this is your setup:
+When configuring your MCP client using the stdio transport, you need to ensure that the MCP server is called using the right version of Python and within the correct working directory. For example, let's pretend this is your setup:
 
 - Your virtual environment is located at `/path/to/your/project/.venv`
 - Your project is located at `/path/to/your/project`
@@ -270,7 +274,7 @@ Then, your MCP client's configuration file should look like this:
 }
 ```
 
-This will ensure that the command used by the MCP client to start the MCP server is the correct version of python and that the environment variables are set correctly.
+This will ensure that the command used by the MCP client to start the MCP server is the correct version of Python and that the environment variables are set correctly.
 
 </Tabs.Tab>
 <Tabs.Tab>