Skip to main content
Glama
new-outlook-mcp

new-outlook-mcp

by michalhron

search_emails

Read-onlyIdempotent

Search archived Outlook for Mac email by keyword or meaning, with filters for sender, date, folder, and attachments; returns summaries and IDs for retrieving full messages and threads.

Instructions

Search archived emails. Returns summaries with an id for get_email/get_thread. freshness says how current the archive is. If warning is present the archive may be missing newer mail: tell the user.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_emails"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNokeyword: exact words (default). semantic: by meaning. hybrid: both, fused. semantic and hybrid need `new-outlook embed` to have been runkeyword
sortNorelevance
limitNo
queryNoFull-text query (SQLite FTS5 syntax: words, "phrases", OR, NOT, prefix*). Searches subject, sender, recipients and body. Omit to filter only.
folderNoFolder name contains this text
offsetNo
senderNoFrom: sender name or address contains this text
accountNoAccount name contains this text
date_toNoLatest date, inclusive, YYYY-MM-DD or ISO 8601 (UTC)
date_fromNoEarliest date, YYYY-MM-DD or ISO 8601 (UTC)
recipientNoTo/Cc/Bcc contains this text
sync_firstNoImport new mail from Outlook's local cache before searching; reported in `sync_first`. Takes a few seconds
has_attachmentNo
attachment_nameNoAn attachment file name contains this text

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnly=true, idempotent=true, destructive=false, so the safety profile is covered. The description adds genuine value beyond that by describing the return payload (summaries plus `id`), the meaning of `freshness`, and the significance of `warning` with a required user-facing action. It says nothing about pagination depth or result-set size behavior, so it remains above baseline but not rich.

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?

Three compact sentences, front-loaded with purpose, then return shape, then the one conditional behavior that matters. Every sentence carries distinct information with no restatement of the name or schema.

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

Completeness4/5

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

For a 14-parameter tool with no output schema, the description covers the essentials an agent cannot get from structured fields: what comes back, what `freshness` means, and what to do about `warning`. Minor gaps remain around result paging and how `sync_first` interacts with archive staleness.

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 71% and the schema itself explains the key parameters, including the mode enum tradeoffs and query syntax. The description adds no parameter-level meaning at all, so it neither compensates for the coverage gap nor detracts; baseline 3 is appropriate.

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 archived emails') and clarifies the boundary with get_email/get_thread, which take an `id` for full content. It does not distinguish this from other retrieval siblings such as list_recent or semantic_search, so it stops short of a 5.

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?

It implies the search-then-fetch workflow by naming get_email/get_thread as follow-ups, and it gives a concrete action to take when `warning` is returned. There is no explicit statement of when to prefer this over other search tools or when filtering-only (omitted query) is appropriate.

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