Skip to main content
Glama
Cresca MCP Server

Cresca MCP Server

Send batch emails (sends real email)

send_batch_emails
Destructive

Sends 1 to 100 different transactional emails in a single all-or-nothing request, using idempotency keys to prevent duplicate batches on retries.

Instructions

WARNING: this SENDS REAL EMAIL to real recipients through Cresca and cannot be undone (only a scheduled or still-queued email can be canceled). Confirm the recipients, sender and content with the user before calling it. Each recipient counts toward the plan's monthly email allowance.

POST /emails/batch. Sends 1 to 100 different emails in one request. Each item takes the same fields as send_email except attachments and scheduled_at, which batches do not support.

All or nothing: if any email is invalid, nothing is sent and the error names the failing email by zero-based index ("Email 3: ...").

Works with sending-access and full-access keys. idempotency_key is required and covers the whole batch: build it from the event ("weekly-digest/2026-W45") and reuse it on every retry. If the result says already_sent, the batch went out earlier: do not retry with a new key. Returns { data: [{ id }, ...] } in request order.

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": {
      "emails": "<emails>",
      "idempotency_key": "<idempotency_key>"
    },
    "name": "send_batch_emails"
  }
}

Input Schema

NameRequiredDescriptionDefault
emailsYes1 to 100 emails. Each item has the same fields as send_email, without attachments or scheduled_at.
idempotency_keyYesRequired. 1 to 256 characters, built from the real-world event this email is about, e.g. "order-confirmation/1042" or "password-reset/<reset request id>". Use the SAME key every time you retry or redo this email (after an error, a timeout or a restart) and a NEW key only for a genuinely new email. Never use a random value or the time. Within 24 hours a repeated key returns the first result instead of sending again.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

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

Goes well beyond the annotations: irreversibility and the narrow cancel window, per-recipient consumption of the monthly allowance, key-scope auth requirement (sending-access or full-access), the all-or-nothing atomicity guarantee, the error indexing format, and the already_sent duplicate state. The required idempotency key is not a contradiction of idempotentHint=false — it is the mechanism that supplies dedupe for an otherwise non-idempotent send.

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 destructive warning is front-loaded in the first line, followed by endpoint, limits, atomicity, auth, idempotency and return shape in that order. Every sentence carries operational information — there is no restatement of the title or filler.

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?

With no output schema, the description supplies the return value ("{ data: [{ id }, ...] } in request order") itself. For a destructive, high-blast-radius batch mutation it also covers reversibility, permissions, retry semantics and failure mode — nothing material 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 coverage is 100%, so the baseline is 3; the description adds meaningful meaning on top by stating that attachments and scheduled_at are unsupported per item, that 1–100 items is the hard range, and that idempotency_key spans the whole batch rather than one email. It also explains the zero-based index used in validation errors, which the schema does not convey.

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?

"POST /emails/batch. Sends 1 to 100 different emails in one request" gives a specific verb, resource and scope, and explicitly contrasts with siblings by noting each item takes the same fields as send_email except attachments and scheduled_at. The cancel caveat ("only a scheduled or still-queued email can be canceled") further separates it from cancel_email.

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 explicit preconditions (confirm recipients, sender and content with the user) and explicit retry rules (reuse the key, do not retry with a new key if already_sent). It implies but never states the direct routing rule "use send_email for a single message," so the alternative selection is left slightly inferential.

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