# Agents are only as good as the context they're given.

Successful marketing isn't about more API calls — it's about understanding what an image actually shows, how an email program is actually performing, and how the experts pull those pieces together. Agentic Tools is the toolkit that hands all three to your agent.

## The problem

### A generic LLM can't see your assets.
It can read a CDN URL. It can't tell you whether that hero shot says "weekend" or "wedding."

### It can't score what you're shipping.
Eight weeks of sends, tone shifts, cadence drift, AI-readiness gaps — invisible without an evaluation layer.

### Best practices live in people's heads.
Without an opinionated playbook, every agent run reinvents what "good" looks like — and lands somewhere safe but generic.

## 01 · Visual context

### Smart Asset Manager MCP.
A digital asset manager built for agents that need to _see_. Search returns matched images as inline pixels alongside the URLs — so the model actually looks at the assets before it picks one, generates a derivative, or drops one into an email.

Images

- search · list · similar · upload
- AI Derivatives 
- Products 
- Bulk Jobs 
- Enrichment Config 
- Account & Analytics

```json
{
  "mcpServers": {
    "cordial-sam": {
      "type": "http",
      "url": "https://sam-mcp.cordial.com/mcp",
      "auth": "oauth"
    }
  }
}
```

```javascript
// search_images returns matched images as inline base64 blocks
// — the model literally looks at them before picking one.
const matches = await mcp.call("search_images", {
  query:    "red running shoe on white background",
  aspect:   "1:1",
  top_k:    8,
});
// → 8 actual images + URLs + metadata in one turn

// Now the agent picks the one that fits the brand,
// not the one whose *filename* sounds right.
const variants = await mcp.call("smart_resize_image", {
  image_id:      matches.images[0].id,
  target_sizes:  ["1080x1080", "1200x628"],
  aspect_ratios: ["16:9"],
});
```

## 02 · Program context

### Understand.email MCP.
The hardest context to give an agent is what your program is actually doing — tone, cadence, offer mix, AI-readiness — over the last eight weeks. Understand.email ingests every send, runs it through an LLM analysis pipeline, and exposes the resulting corpus through an MCP server.

```json
{
  "mcpServers": {
    "understand-email": {
      "type": "http",
      "url": "https://understand.email/mcp",
      "auth": "oauth"
    }
  }
}
```

```javascript
→ tool_call: account_status
← { ready: true, scope: "brand.com", paid: false }

→ tool_call: get_domain_audit { root_domain: "brand.com" }
← {
    weighted_overall: 6.8, grade: "B-",
    priority_focus_areas: [
      { category: "C2 · AI Summary Readiness",      median: 4.1 },
      { category: "C3 · Schema.org / Annotations",  median: 2.0 },
      { category: "C5 · Signal-to-Noise Ratio",     median: 5.4 }
    ],
    window: "8 weeks, ending 2026-05-24"
  }

→ tool_call: list_domain_audit_emails
       { root_domain: "brand.com", max_score: 5, limit: 5 }
← [ { email_id: "e_91…", overall: 3.4, subject: "Last chance!" }, … ]
```

### Inside the AI-readiness audit

### 7 categories of program context. Letter grades A+ → F.

C1 weight 20%  
Value-Prop Clarity  
Subject, headline, body sub-scores

C2 weight 20%  
AI Summary Readiness  
How well Gemini & Apple summarize it

C3 weight 5%  
Schema / Annotations  
Schema.org + Gmail annotations

C4 weight 20%  
Plain Text & Alt Tags  
Accessibility & summarization base

C5 weight 15%  
Signal-to-Noise  
Information density per send

C6 weight 10%  
Frequency / Coordination  
Domain-level cadence quality

C7 weight 10%  
Personalization Depth  
Merge tags + image personalization

## 03 · Opinionated playbooks

### The Agentic Cookbook.
Pixels and program data only get you halfway. The other half is knowing how to _use_ them — how an expert email marketer would sequence the work, what tradeoffs to make, which signals actually matter. That craft lives in our team's heads. The Agentic Cookbook moves it into your agent.

```bash
# Pull the cookbook
git clone https://github.com/CordialExperience/agentic-cookbook
cd agentic-cookbook

# Install a skill into Claude Code
cp -r skills/<skill-name> ~/.claude/skills/
```

## Give your agent the context. Watch what it builds.
The cookbook is open source. Understand.email is free to try — no Cordial account required. SAM MCP runs the moment you have a SAM tenant.