DirectMailAmerica — Full

Preview Email Letterhead

preview_email_letterhead

Read-onlyIdempotent

No charge. Render an unsaved canvas/PDF letterhead with {letterhead:save-input,sample:true,body?} as an embedded private PDF resource. sample defaults true; omitted body uses the built-in sample, body:"" intentionally leaves it blank (max 5000 characters). sample:false returns blank stationery. Workspace authentication required; staging may preview. No saving, consent, pricing or mailing. Preview includes layout margins and ruling when sample:true.

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": {
      "letterhead": "<letterhead>"
    },
    "name": "preview_email_letterhead"
  }
}

Input Schema

Name	Required	Description
`body`	No	With sample:true, omission uses the built-in sample; an empty string leaves the body blank. Ignored when sample:false.
`sample`	No
`letterhead`	Yes

Output Schema

Name	Required	Description	Default
`uri`	No
`error`	No
`pages`	No
`filename`	No
`mimeType`	No
`operation`	Yes
`sizeBytes`	No
`priceCents`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 31, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "description": "Read operation first for financial/mail state and recovery. Optional service fields are absent on failure. Unknown is not zero or permission to retry. Legacy service fields remain available.",
+  "properties": {
+    "error": {
+      "type": "string"
+    },
+    "filename": {
+      "type": "string"
+    },
+    "mimeType": {
+      "type": "string"
+    },
+    "operation": {
+      "additionalProperties": false,
+      "properties": {
+        "amountCents": {
+          "description": "USD cents. Null means not applicable or not known; never interpret null as zero.",
+          "type": [
+            "integer",
+            "null"
+          ]
+        },
+        "code": {
+          "type": "string"
+        },
+        "currency": {
+          "const": "USD"
+        },
+        "expiresAt": {
+          "type": [
+            "string",
+            "null"
+          ]
+        },
+        "fundsState": {
+          "enum": [
+            "none",
+            "reserved",
+            "debited",
+            "captured",
+            "credited",
+            "refunded",
+            "unknown",
+            "simulated"
+          ]
+        },
+        "mailingState": {
+          "enum": [
+            "none",
+            "submitted",
+            "pending",
+            "unknown",
+            "simulated"
+          ]
+        },
+        "receiptId": {
+          "type": [
+            "string",
+            "null"
+          ]
+        },
+        "recovery": {
+          "additionalProperties": false,
+          "properties": {
+            "action": {
+              "enum": [
+                "none",
+                "retry_same_request",
+                "check_existing_job",
+                "fresh_approval",
+                "requires_user_action"
+              ]
+            },
+            "instructions": {
+              "type": "string"
+            },
+            "nextTool": {
+              "type": [
+                "string",
+                "null"
+              ]
+            },
+            "safeToRetry": {
+              "type": "boolean"
+            }
+          },
+          "required": [
+            "action",
+            "safeToRetry",
+            "nextTool",
+            "instructions"
+          ],
+          "type": "object"
+        },
+        "requestId": {
+          "type": "string"
+        },
+        "status": {
+          "enum": [
+            "succeeded",
+            "failed",
+            "pending",
+            "needs_review"
+          ]
+        },
+        "tool": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "requestId",
+        "tool",
+        "status",
+        "code",
+        "amountCents",
+        "currency",
+        "expiresAt",
+        "receiptId",
+        "fundsState",
+        "mailingState",
+        "recovery"
+      ],
+      "type": "object"
+    },
+    "pages": {
+      "type": "integer"
+    },
+    "priceCents": {
+      "type": "integer"
+    },
+    "sizeBytes": {
+      "type": "integer"
+    },
+    "uri": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "operation"
+  ],
+  "type": "object"
+}

First observedOct 22, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description still adds real context: no charge, workspace authentication required, staging previews allowed, output is an embedded private PDF, and no consent/pricing/mailing side effects occur. That is exactly the beyond-annotation detail that prevents an agent from over-anticipating costs or side effects.

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?

Dense and front-loaded — the render action and its private-PDF output come first, then parameter rules, then side-effect exclusions. The compressed '{letterhead:save-input,sample:true,body?}' notation is efficient but reads as shorthand that takes a pass to parse.

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

Completeness5/5

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

Covers what an agent needs before calling: no cost, auth requirement, no persistence, and a note that the preview includes layout margins and ruling when sample:true. An output schema exists, so the return payload itself need not be explained further.

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

Parameters4/5

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

With only 33% schema description coverage the description has to carry weight, and it does for the two scalars: sample defaults to true, omitted body falls back to the built-in sample while body:"" intentionally blanks it, plus the 5000-char cap and sample:false behavior. The large letterhead object is handled only by the pointer '{letterhead:save-input}', which relies on the agent knowing the save tool's shape rather than describing the canvas-vs-PDF source distinction directly.

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

Purpose5/5

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

States a specific verb and resource — 'Render an unsaved canvas/PDF letterhead ... as an embedded private PDF resource' — and immediately separates itself from the save path with 'unsaved' and 'No saving'. An agent can distinguish this from save_email_letterhead and download_email_letterhead without opening a schema.

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

Usage Guidelines4/5

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

Gives clear usage context ('No charge', 'staging may preview', sample:false returns blank stationery) and an explicit exclusion ('No saving, consent, pricing or mailing'), which implies save_email_letterhead is the write path. It stops short of naming sibling preview tools (preview_email_letter, preview_letter), so the routing is implied rather than spelled out.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All DirectMailAmerica — Full tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?