Fix/edit docs duplication and typos (#44)

Author: gitkola

docs/src/docs/core/performance.md

@@ -32,13 +32,6 @@ async function analyticsEffect(context: RequestContext, response: MessageRespons
 
 ## Measures vs Marks
 
-This concept comes from [Web Performance API](https://developer.mozilla.org/en-US/docs/Web/API/Performance).
-Marks are just named 'sequences' for the performance tool to measure.
-Let's say that you have a tool for your AI, and you'd like to check how it performs.
-Issue might be that it's being triggered multiple times by AI. For that reason
-one mark can be a part of multiple measures.
-Single measure is constructed of two marks: `start` and `end`.
-
 This concept is inspired by the [Web Performance API](https://developer.mozilla.org/en-US/docs/Web/API/Performance). Marks are essentially named sequences that the performance tool uses to measure execution time. For instance, if you have a tool for your AI and want to evaluate its performance, you might find it triggered multiple times by the AI. Therefore, a single mark can be part of multiple measures. A measure is constructed using two marks: `start` and `end`.
 
 :::info

docs/src/docs/core/plugins.md

@@ -84,7 +84,7 @@ The order of plugins is important! Depending on the call to `next`, they are exe
 - Top-down before the call to `next`
 - Bottom-up after the call to `next`
 
-## Midleware early return
+## Middleware early return
 
 Your middleware can also break the execution chain early, stopping the execution of any subsequent middleware.
 

docs/src/docs/core/references.md

@@ -7,7 +7,7 @@ When a tool call is triggered, you can add references to the context and later u
 References are not automatically added for the AI. You need to implement this functionality if needed.
 :::
 
-Let's create middleware that adds relevant weather information to the context.
+Let's create a tool that adds relevant weather information to the context.
 
 ```js
 async function queryWeather(

docs/src/docs/core/tools.md

@@ -10,15 +10,10 @@ OpenAI has implemented tools, but not all AI providers do.
 
 ## Adding tools
 
-First lets start by implementing the tool function. There are two inputs for it `params` that are decided
-by the AI and context that is passed by byorg. Tool function has to return a string, as the information
-returned by it will be then passed back to AI as an 'addition' to system prompt.
-
 To start, implement the tool function. It takes two inputs: `params`, which are determined by the AI, and `context`, which is passed by byorg.
 The tool function must return a string, as this information will be passed back to the AI as an addition to the system prompt.
 
 ```js
-
 async function queryUsers(params: { query: string }, context: RequestContext): Promise<string> {
   const { query } = params;
   const { references } = context;

docs/src/docs/core/usage.mdx

@@ -46,6 +46,6 @@ Here is step by step how to start with byorg.
 
 {/* prettier-ignore-end */}
 
-That's it! Your message is being handled an processed by byorg.
+That's it! Your message is being handled and processed by byorg.
 
 In next sections we will go through customisation, error handling and changing LLM provider, to better suit your needs.