Skip to main content
Glama
new-outlook-mcp

new-outlook-mcp

by michalhron

search_files

Read-onlyIdempotent

Search orphaned Outlook Files cache entries—attachments and message bodies no longer tied to archived mail—by full-text query, kind, and file date; read hits via attachment_id.

Instructions

Search files in Outlook's Files/ cache that belong to no archived message (attachments and bodies of mail that has left the cache). Read one with get_attachment using its attachment_id ('orphan:'). Dates are file dates, not send dates. Use search_emails for mail itself.

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_files"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoattachment: attachment files; body: cached message bodies
limitNo
queryNoFull-text query (FTS5 syntax) over file name and text. Omit to list the newest files.
offsetNo
date_toNoLatest file date, inclusive
date_fromNoEarliest file date, YYYY-MM-DD or ISO 8601 (UTC)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint and non-destructive, so safety is covered; the description adds genuinely non-obvious behavior: results are orphaned files only, and dates are file dates rather than send dates. It stops short of describing result shape or pagination/ordering behavior beyond the schema's default.

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?

Four short sentences, front-loaded with the scope constraint, followed by the retrieval path, the date caveat, and the sibling alternative. Dense and purposeful, with only mild awkwardness in the parenthetical definition of orphan files.

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?

No output schema exists, yet the description supplies the concept (orphaned files), the identifier format for retrieval ('orphan:<n>'), and the date semantics, which is most of what an agent needs to call and use it. Only the returned fields and pagination mechanics are left unstated.

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 67%, covering query (FTS5), kind, and the date bounds. The description adds meaning the schema lacks by disambiguating date_from/date_to as file dates, not send dates, which is the main way to misread this tool; it does not explain limit/offset behavior, but those are conventional.

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 and resource plus a precise scope: files in Outlook's Files/ cache that belong to no archived message, spelling out that this means attachments and bodies of mail that has left the cache. It explicitly distinguishes itself from search_emails, so an agent can pick between them without opening either 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?

Gives the alternative and the condition that selects it ('Use search_emails for mail itself') and the follow-up path for acting on results ('Read one with get_attachment using its attachment_id'). Both the when and the what-next are explicit.

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