Skip to main content
Glama

Generate a reply to an e-mail for a chosen intent

email_reply
Read-only

Drafts a reply (subject and body) to a received e-mail (max 10,000 characters) for an intent: accept, decline, ask-information, follow-up or custom with your own instructions. Tone formal, neutral or friendly; language as requested. Dates, numbers and names that are not in the inputs appear as placeholders such as [date]. Read it before sending. Related tools on this server, for a different need: email_check when you need to check e-mail addresses without sending mail. Price: $0.002 per successful call, paid with x402 (USDC on Base, Solana and 10 more networks); failed calls are not charged.

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": {
      "email": "<email>",
      "intent": "<intent>"
    },
    "name": "email_reply"
  }
}

Input Schema

NameRequiredDescriptionDefault
toneNoformal, neutral (default) or friendly
emailYesThe e-mail you received (max 10,000 characters)
intentYesaccept, decline, ask-information, follow-up or custom
languageNoLanguage code or name of the reply, default en
instructionsNoYour own instructions (max 500 characters), required for intent custom

Output Schema

NameRequiredDescriptionDefault
bodyNo
noteNo
toneNo
intentNo
subjectNo
languageNo
checkedAtNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changed
    • addedOutput schema / properties / body
      Added value: +{}
    • addedOutput schema / properties / checkedAt
      Added value: +{}
    • addedOutput schema / properties / intent
      Added value: +{}
    • addedOutput schema / properties / language
      Added value: +{}
    • addedOutput schema / properties / note
      Added value: +{}
    • addedOutput schema / properties / subject
      Added value: +{}
    • addedOutput schema / properties / tone
      Added value: +{}
  2. Added

TDQS

A4.1/5.0
Behavior4/5

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

Annotations only declare readOnlyHint and openWorldHint; the description adds genuinely new behavior: unknown dates/numbers/names become placeholders like [date], the output is a draft to be reviewed before sending, and billing is $0.002 per successful call with failures uncharged. It stops short of saying whether the draft is ever transmitted or what payment handshake looks like step by step, so it is not a full behavioral picture.

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?

Core capability, constraints and placeholder behavior are front-loaded in the first two sentences, and the cost sentence is decision-relevant. The sibling aside and pricing tail lengthen it slightly beyond what is needed to invoke the tool correctly.

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

Completeness4/5

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

With an output schema present, return-format detail is unnecessary, and the description covers the remaining gaps an agent needs: intent options, placeholder artifacts, human review before sending, and per-call cost. Only minor items, such as limits on the input e-mail beyond character count, are left implicit.

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

Parameters3/5

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

Schema coverage is 100%, so intent values, tone options, language default and the 500-character instructions limit are already documented in structured fields; the description largely restates them. The one piece of added meaning is that facts absent from the inputs surface as bracketed placeholders, which tells the caller to supply names/dates to avoid them.

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 names a specific verb and artifact ('Drafts a reply (subject and body) to a received e-mail'), states the intent-driven variants, and enumerates the tone/language knobs. It also explicitly separates itself from the one named sibling by need ('email_check when you need to check e-mail addresses without sending mail').

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?

It gives a clear context (replying to a received e-mail for a chosen intent) and an explicit hand-off rule for email_check, plus a workflow cue ('Read it before sending') that frames this as draft generation, not sending. It does not state exclusions such as message types it can't handle or when to prefer writing a reply manually.

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.

Resources