Skip to main content
Glama
agentisend

agentisend

Get a received email

get_received_email
Read-onlyIdempotent

Read a single received email by ID to inspect headers, text and HTML bodies, delivery verdict with reasons, and attachment metadata, including held messages only when requested.

Instructions

Purpose: read one received email — headers, text and HTML bodies as data, the verdict (clear, review, or unavailable) with its reasons, and the attachments it carried. A held message is left out unless include_held is true. Held mail is waiting for a person to release it and is not in the arrival webhook yet. NOT for: listing (list_received_emails) or sending a reply (reply_to_email). The HTML is what a stranger sent; it is not rendered here. Returns: the message, its headers, both bodies, extracted_text and extracted_html (the reply with quoted history, signatures and footers removed; null when that cut could not be produced, in which case read text then html), inbound_verdict, and attachment metadata. Attachment bytes are a REST download, not this tool. A list does not include the extracted fields.

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": {
      "received_id": "<received_id>"
    },
    "name": "get_received_email"
  }
}

Input Schema

NameRequiredDescriptionDefault
received_idYesThe id from list_received_emails.
include_heldNoSet true to read a message a person has not released yet. Omitted, a held message is left out.

Output Schema

NameRequiredDescriptionDefault
idNoIdentifier.
htmlNoThe HTML part as it arrived.
textNoThe plain-text part as it arrived.
errorNoPresent instead of the fields above when the call was refused: code, message, fix, docs_url, retryable and, when waiting helps, retry_after_seconds.
extracted_htmlNoThe same cut, in HTML. Null when the message had no HTML or extraction produced nothing.
extracted_textNoThe reply with quoted history, signatures and footers removed. Null when extraction produced nothing; read text, then html.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive), but the description adds real behavior: held messages are silently excluded unless include_held is set, extracted fields may be null with a fallback order, and attachment bytes require a separate REST download. It stops short of describing pagination, but that is not applicable to a single-object read.

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?

Front-loaded with explicit Purpose / NOT for / Returns labels, which makes it scannable. The Returns paragraph partly duplicates the output schema's job and could be trimmed, but the rest is dense with non-redundant information.

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 two-parameter read tool with an output schema, the definition covers selection guidance, the held-message gotcha, and where attachment bytes live. Nothing an agent needs to call it correctly 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 baseline is 3, but the description adds meaning beyond the schema: it explains what 'held' means (awaiting human release, not yet in the webhook) and that omitting include_held drops the message rather than erroring. That is genuine semantic value, not restatement.

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?

Names a specific verb and resource ('read one received email') and enumerates what it yields: headers, both bodies, the verdict with reasons, and attachment metadata. It also explicitly separates itself from the list and reply siblings, so an agent can pick it without opening a schema.

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?

States when to use it (single message read) and when not to ('NOT for: listing (list_received_emails) or sending a reply (reply_to_email)'), naming both alternatives. It also spells out the held-message condition and why held mail is absent from the arrival webhook.

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