Skip to main content
Glama
BeeL MCP server

BeeL MCP server

Official
by beel-es

beel_list_email_deliveries

Read-onlyIdempotent

Lists an account's recorded email deliveries, including queued and rejected attempts, with filters by type, status, recipient, and related entity; read-only history, no sending or resending.

Instructions

Returns the emails the system recorded on behalf of the account in the path: invoice deliveries, verification, onboarding. It only reads the history; it does not send or resend anything.

  • Every attempt is recorded, not only the ones that went out: an email stopped by policy is listed with status REJECTED, and one accepted but not dispatched yet as QUEUED, rather than being omitted.

  • Order: by sent_at descending, configurable with sort_by / sort_order.

  • Filters: type, status, recipient and related_entity_id.

  • sent_at: the moment the message was handed over, so it is absent while an email is still QUEUED.

  • Scope: the account is the one named in the path; the environment is not, and comes from the credential.

BeeL API endpoint: GET /v1/accounts/{account_id}/emails (reference: https://docs.beel.es)

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": {
      "account_id": "<account_id>"
    },
    "name": "beel_list_email_deliveries"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNoPage number, starting at 1. The response echoes it back as `pagination.current_page`.
typeNoFilter by email type (e.g. INVOICE_EMITTED)
limitNoHow many items to return per page. The response echoes it back as `pagination.items_per_page`.
statusNoFilter by delivery status
sort_byNoField to sort bysent_at
recipientNoFilter to emails where any recipient contains the term (case-insensitive)
account_idYesYour own account, or an account you provisioned. It — not the credential — decides which account the operation acts on; a `403` is returned when you do not reach it, the same response an account that does not exist gets.
sort_orderNoSort order directiondesc
related_entity_idNoFilter to emails associated with a given related entity (e.g. an invoice id)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.10.0
    • addedInput schema / properties / sort_by / type
      Added value: +"string"
    • addedInput schema / properties / sort_order / type
      Added value: +"string"
    • addedInput schema / properties / status / type
      Added value: +"string"
  2. Changed1 schema field changedv0.9.0
    • changedInput schema / $defs / EmailDeliverySortBy / description
      Previous value: -"Email delivery field the list is ordered by."New value: +"Email delivery field the list is ordered by: `sent_at` the instant of the attempt,\n`status` the delivery status, `email_type` the kind of email.\n"
  3. Changed3 schema fields changedv0.5.0
    • removedInput schema / $defs / EmailDeliverySortBy / example
      Removed value: -"sent_at"
    • removedInput schema / $defs / SortOrder / example
      Removed value: -"desc"
    • addedInput schema / additionalProperties
      Added value: +false
  4. First observedv0.3.1

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare read-only, idempotent, non-destructive, but the description adds genuinely new behavioral facts: every attempt is recorded (REJECTED and QUEUED included rather than omitted), default ordering by sent_at descending, and that sent_at is absent while QUEUED. The account-versus-environment scoping note is exactly the kind of context an agent cannot infer from annotations.

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?

Lead sentence states the operation and the negative constraint before any bullets, and each bullet covers exactly one distinct fact (completeness of history, ordering, filters, sent_at semantics, scope) with no repetition. The docs URL at the end is a single-line pointer, not padding.

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?

For a 9-parameter read-only list endpoint with full schema coverage and no output schema, the description covers everything an agent needs: what is returned, in what order, how to filter, how status semantics affect presence of sent_at, and which account/environment is targeted. Nothing material is left to inference.

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 earns above that by explaining that ordering is by sent_at descending and configurable, enumerating the filter axes, and flagging the sent_at-absent-while-QUEUED behavior that affects how sort and filter results should be read. It does not add syntax or matching details beyond what the schema already documents, so it stays short of a 5.

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 (returns) and resource (emails recorded on behalf of the account) and immediately scopes the content types: invoice deliveries, verification, onboarding. The second sentence explicitly negates the sending behavior, which cleanly separates it from siblings like beel_create_invoice_delivery and beel_send_invoice.

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?

The 'it only reads the history; it does not send or resend anything' clause gives a clear when-to-use boundary against the delivery/send siblings, and the scope bullet clarifies that the account comes from the path while the environment comes from the credential. It stops short of naming a specific alternative (e.g. beel_get_email_delivery for a single record, or beel_get_email_delivery_indicators for aggregates), so the routing is implied rather than explicit.

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

Deploy Server

Other Tools