himalaya-mcp

Overview Schema Source Related Servers Discussions Admin

create_action_item

Extract action items, todos, deadlines, and commitments from an email and return structured results for creating tasks, reminders, or calendar events.

Instructions

Read an email and extract action items, todos, deadlines, and commitments. Returns structured action items that can be used to create tasks, reminders, or calendar events.

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": {
      "id": "<id>"
    },
    "name": "create_action_item"
  }
}

Input Schema

Name	Required	Description
`id`	Yes	Email message ID
`folder`	No	Folder name (default: INBOX)
`account`	No	Account name (uses default if omitted)
`destination`	No	File path to save action items (optional). Writes a markdown file with extracted action items.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv2.2.2Nov 7, 2026

addedInput schema / properties / id / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "maximum": 9007199254740991,
+    "minimum": 0,
+    "type": "integer"
+  }
+]

removedInput schema / properties / id / type
```
Removed value: -"string"
```

Changed1 schema field changedv2.0.0Jul 25, 2026

addedInput schema / properties / destination

Added value: +{
+  "description": "File path to save action items (optional). Writes a markdown file with extracted action items.",
+  "type": "string"
+}

First observedv1.7.0Jun 21, 2026

TDQS

A3.5/5.0

Behavior3/5

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

No annotations, so the description carries the full behavioral burden. It discloses that the email is read and that structured items are returned, which are useful signals, but says nothing about whether reading has side effects (e.g., marking the message as read), how faithfully items are extracted, or that passing destination additionally writes a markdown file to disk.

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?

Two sentences, front-loaded with the core action and followed by the return value. No redundancy, no filler.

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

Completeness3/5

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

There is no output schema, so the description is the only source for what is returned, and 'structured action items' is a sketch rather than a shape (fields, confidence, handling of emails with no items). The extraction semantics and the optional file-write side effect are not covered, which leaves real gaps for a tool with four parameters and no annotations.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema itself already documents id, folder, account, and the destination write behavior. The description adds no parameter-level meaning beyond that and does not mention the destination file output at all, leaving the schema to do all the work.

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?

States a specific verb+object pair and goes beyond the name: 'Read an email and extract action items, todos, deadlines, and commitments' tells the agent this is an extraction/analysis operation, not just a read. It is distinguishable from read_email by naming the extracted artifact types, though it does not explicitly contrast itself with the siblings.

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

Usage Guidelines3/5

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

The stated purpose implies usage (turn an email into follow-up tasks), and the mention of 'structured action items' hints at a downstream step. But there is no explicit when-to-use vs read_email, extract_calendar_event, or create_reminder, and no stated prerequisites or exclusions.

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