diff --git a/guides/ai-agents/mcp-servers.mdx b/guides/ai-agents/mcp-servers.mdx
index fc4d7a21..d8c22faa 100644
--- a/guides/ai-agents/mcp-servers.mdx
+++ b/guides/ai-agents/mcp-servers.mdx
@@ -68,6 +68,35 @@ MCP servers are configured per project and can be attached to one or more agents
   Per-user OAuth (where each user connects their own account) is planned but not yet supported.
 </Info>
 
+## Choose which tools are exposed to the agent
+
+Each MCP server exposes a set of tools, and you decide which ones the agent can use. Open an MCP server in your project settings and use **Tool permissions** to enable just the tools that fit the agent's job.
+
+<Frame>
+  <img
+    src="/images/guides/ai-agents/mcp-tool-curation.png"
+    alt="MCP server tool permissions view showing the Notion MCP server with one of fourteen tools enabled"
+  />
+</Frame>
+
+A few ways teams use this:
+
+- **Stick to read-only when that's all you need.** Enable tools like `search` or `fetch` and leave write tools (create, update, delete) off so the agent can look things up without changing anything.
+- **Match tools to the agent's role.** A support insights agent probably needs to read Notion pages, not move or delete them.
+- **Open things up gradually.** Start with a small set of tools and add more as you see how the agent uses them.
+
+## Pick the right MCPs and tools for each agent
+
+Every enabled tool — its name, description, and parameter schema — is included in the agent's context on every turn. That context is shared with instructions, conversation history, and the model's own reasoning, so a long menu of tools leaves less room for the things that make answers good.
+
+The fix is simple: be intentional about what you turn on.
+
+- **Build agents around a job.** A focused product analytics agent or RevOps agent usually beats one general-purpose agent with every MCP attached.
+- **Attach the MCPs that agent actually uses.** If a product analytics agent never touches Confluence, don't connect it.
+- **Enable the specific tools for the task.** Within an MCP, turn on the handful of tools the agent needs and leave the rest off.
+
+This isn't a reason to avoid MCPs — they're what makes agents useful. It's just worth picking a curated set per agent rather than enabling everything by default.
+
 ## Example agents
 
 **Product analytics agent + Linear**
diff --git a/guides/formatting-your-fields.mdx b/guides/formatting-your-fields.mdx
index bc047bdc..998f7a35 100644
--- a/guides/formatting-your-fields.mdx
+++ b/guides/formatting-your-fields.mdx
@@ -1019,7 +1019,7 @@ Currently you can format 2 types of fields in the Lightdash UI:
 You can adjust the formatting of your pre-defined metrics from the results table.
 
 <Frame>
-  <img src="/images/guides/formatting-your-fields/yaml-metric-formatting.jpg"/>
+  <img src="/images/guides/formatting-your-fields/yaml-metric-formatting.png"/>
 </Frame>
 
 You can customize the formatting of your custom metrics when you create them, and later on from the results table.
@@ -1085,4 +1085,4 @@ You can then choose from the following formatting types:
   * `separator`, e.g. from `.` to `,`
   * `compact` value to compact your metric to a certain unit, e.g. from `1,000,000` to `1M`
   * `prefix` value to add a prefix to your metric, e.g. `+` or `-`
-  * `suffix` value to add a suffix to your metric, e.g. `%`
\ No newline at end of file
+  * `suffix` value to add a suffix to your metric, e.g. `%`
diff --git a/images/guides/ai-agents/mcp-tool-curation.png b/images/guides/ai-agents/mcp-tool-curation.png
new file mode 100644
index 00000000..829d0ce3
Binary files /dev/null and b/images/guides/ai-agents/mcp-tool-curation.png differ