Sergio by Serviche

Send an email (after your person confirms)

send_email

DestructiveIdempotent

Emails a client from the business mailbox on your person's order, as a Manual send under the business's Sending setting. First call without confirm_token: nothing is sent; you get a preview (to, subject and the exact text) and a confirm_token. Show your person the preview word for word, and only after they say yes, call again with the same arguments and the SAME idempotency_key, plus confirm_token. replyToEmailId threads it as a reply to that inbound email.

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": {
      "conversation_id": "<conversation_id>",
      "to": "<to>",
      "subject": "<subject>",
      "body": "<body>",
      "idempotency_key": "<idempotency_key>"
    },
    "name": "send_email"
  }
}

Input Schema

Name	Required	Description
`to`	Yes
`body`	Yes
`subject`	Yes
`confirm_token`	No	From the preview, after your person said yes. Leave it out to get the preview.
`replyToEmailId`	No
`conversation_id`	Yes
`idempotency_key`	Yes	Your id for this operation (8-128 of A-Z a-z 0-9 . _ : -). Reuse it on every retry of the same operation; use a new one for a new operation.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 8, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Goes well beyond the annotations by disclosing the dry-run preview behavior, exactly what the preview contains, the idempotency-key reuse rule, and reply threading via replyToEmailId. What it does not cover is what happens on token expiry, or how a 'Manual send' setting blocks or queues the send — useful context given destructiveHint=true.

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?

Front-loads the core action, then the two-phase flow in execution order, then the optional threading parameter. Dense but zero filler; each sentence carries a distinct operational fact.

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?

For a 7-parameter, destructive, no-output-schema tool, the description covers the risky parts (preview, confirmation, idempotency) well enough to call safely. Missing only the meaning of conversation_id and any note on preview/token lifetime, which keeps it short of full completeness.

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 29% schema description coverage, the description does real work: it explains confirm_token's two-phase role, idempotency_key reuse across retries, and that replyToEmailId threads the email as a reply to an inbound message. The notable gap is conversation_id, a required parameter never mentioned in the description, so an agent must guess what conversation it ties the email to.

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 ('Emails a client from the business mailbox') and qualifies the channel and origin ('on your person's order, as a Manual send under the business's Sending setting'). The email-specific framing distinguishes it from text/campaign siblings like send_text and send_campaign_messages without naming them.

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

Usage Guidelines5/5

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

Gives an explicit two-call protocol: first call without confirm_token yields a preview and nothing is sent; a second call with confirm_token and the same idempotency_key actually sends. It also states the gating condition ('only after they say yes') and the required human step ('show your person the preview word for word'), leaving nothing to inference.

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

All Sergio by Serviche 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?