Skip to main content
Glama

Draft a Letter

draft_letter

Create a letter DRAFT: verifies the recipient address with PostGrid, screens content, and returns a price quote. This NEVER mails anything.

Pass EITHER html (letter body as an HTML string) OR pdf_path (path to a PDF file on the server). PDF text is extracted for screening; if extraction fails the draft is kept but flagged needs_review.

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": {
      "api_key": "<api_key>",
      "to": "<to>",
      "from_address": "<from_address>"
    },
    "name": "draft_letter"
  }
}

Input Schema

NameRequiredDescriptionDefault
toYesrecipient address dict with name, address_line1, address_city, address_state, address_zip (US).
htmlNoletter body as an HTML string (use this OR pdf_path).
colorNoTrue for color printing, False for black & white.
api_keyYesyour 3L-Group Technology API key (lms_...).
pdf_pathNoserver-local path to a PDF to mail instead of html.
quantityNonumber of identical letters (10+ gets the bulk rate).
certifiedNoOPT-IN ONLY — True for USPS Certified Mail with Electronic Receipt (tracked, signature on delivery). Defaults to False, which sends standard First Class mail. Only set True when the customer explicitly asked for certified mail: it costs significantly more (PostGrid's certified rate + the flat $1.00 service fee, roughly $11 per letter). Never default this to True.
descriptionNooptional label for your own records.
from_addressYessender address dict, same shape as `to`.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

The description adds important behavior beyond the annotations: it performs PostGrid address verification, screens content, returns a price quote, never mails, and keeps a draft flagged as needs_review if PDF text extraction fails. These details are highly relevant for a tool with openWorldHint=true and readOnlyHint=false.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short, front-loaded, and structured around the critical safety fact that this never mails. Every sentence carries useful information, and the html/pdf_path constraint is stated clearly without waste.

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?

Given the rich schema, annotations, and presence of an output schema, the description provides all the critical behavioral context an agent needs: draft-only safety, verification/screening steps, price quote return, and PDF extraction fallback behavior. No essential invocation detail is missing.

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?

Schema description coverage is 100%, so the schema already carries most parameter meaning. The description still adds useful semantics around the html/pdf_path choice and explains that PDF text is extracted for screening, with a specific failure behavior.

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?

The description uses a specific verb and resource ("Create a letter DRAFT") and immediately adds distinguishing scope: address verification, content screening, price quote, and no mailing. An agent can tell this is a draft-creation tool rather than a send tool without needing additional context.

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

Usage Guidelines3/5

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

The description makes clear this tool never mails anything, which implies it is for drafting rather than sending. However, it does not explicitly state when to use it versus related send/request tools or name any alternate path, so usage guidance is present but mostly implied.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.