Skip to main content
Glama
@marlinjai/email-mcp

@marlinjai/email-mcp

by marlinjai

email_search

Search emails across Gmail, Outlook, iCloud, and IMAP accounts using filters for sender, subject, date, folder, and attachments, returning compact results unless full bodies are requested.

Instructions

Search emails with filters. By default returns compact results without full body content to save context. Set returnBody=true to include full email bodies.

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": {
      "accountId": "<accountId>"
    },
    "name": "email_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNo
bodyNo
fromNo
limitNo
sinceNo
beforeNo
folderNo
offsetNo
subjectNo
accountIdYes
returnBodyNoInclude full email body in results (default: false). Set to true only when you need the full content.
unreadOnlyNo
starredOnlyNo
hasAttachmentNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.11.0

TDQS

C2.9/5.0
Behavior3/5

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

With no annotations at all, the description carries the full burden, and it does add one genuinely useful behavioral fact: results are compact by default and full bodies are opt-in for context economy. However, it never states that the operation is read-only, how limit/offset paginate or default, result ordering, or any cap on returned items.

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?

Three short sentences, front-loaded with purpose and followed by the default/override behavior; nothing is wasted. The second sentence slightly restates what the schema already says about returnBody, costing it a perfect score.

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

Completeness2/5

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

A 14-parameter, unannotated search tool with no output schema needs substantially more explanation than this. Missing are date format conventions, pagination defaults, and a description of the result shape (what a "compact" result contains), which the agent needs to use the filters correctly.

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

Parameters2/5

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

Schema description coverage is 7% across 14 parameters, so the description must compensate and it does not. Only returnBody is explained; the semantics and formats of since/before (string dates of unknown format), body, from, to, folder, limit, and offset are left entirely undocumented in both places.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb+resource ("Search emails with filters"), which is clearly distinct from retrieval siblings like email_get or email_get_thread. It is clear what the tool does, but it never characterizes the filter set, so the agent must open the schema to learn what can actually be searched on.

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

Usage Guidelines2/5

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

There is no when-to-use guidance and no mention of alternatives — nothing tells the agent to prefer email_get for a known ID or email_get_thread for conversations. The only conditional instruction is about returnBody, which is about output size rather than tool selection.

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