mac-messages-mcp

Overview Schema Source Related Servers Discussions Admin

tool_search_attachments

Search Messages attachments by date range, contact, or MIME type to locate specific files, returning metadata only.

Instructions

Search message attachments by date range, contact, and MIME type.

This is read-only and returns metadata only; it does not return file bytes or
modify attachments. Requires Full Disk Access for the host app or terminal.
Filenames, MIME types, paths, and sender labels are structurally neutralized
and wrapped in <untrusted-mcp-output>. Use this to find candidate files
cheaply, then call tool_get_attachment for one specific attachment. Use
tool_fuzzy_search_messages when searching message text instead of attachment
metadata.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	Maximum number of attachment metadata rows to return.
`contact`	No	Optional contact name, phone number, or email address filter.
`end_date`	No	Optional inclusive end date in "YYYY-MM-DD" format.
`mime_type`	No	Optional MIME type or prefix filter, such as "image/" or "application/pdf".
`start_date`	No	Optional inclusive start date in "YYYY-MM-DD" format.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Addedv1.1.0Sep 7, 2026

TDQS

A4.6/5.0

Behavior5/5

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

No annotations were provided, so the description carries the full burden. It discloses that the tool is read-only, returns metadata only, does not return file bytes, does not modify attachments, requires Full Disk Access, and structurally neutralizes untrusted content (filenames, MIME types, paths, sender labels). These details fully inform the caller of side effects, permissions, and security measures.

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?

The description is concise and well-structured, but contains some redundancy (the neutralization sentence is repeated verbatim from the schema context). Still, it is efficient and front-loaded with the core purpose.

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?

Given a moderate number of parameters (5, none required) and the presence of an output schema, the description provides sufficient context: it states the search criteria, clarifies the read-only metadata-only nature, notes the permission requirement, and positions the tool among alternatives. No additional context is needed for a caller to decide when and how to use it.

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% (all 5 parameters have descriptions). The tool description does not add significant extra parameter information beyond the schema, so the baseline of 3 applies.

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?

The description clearly states that the tool searches message attachments by date range, contact, and MIME type, and explicitly contrasts it with related tools (tool_get_attachment, tool_fuzzy_search_messages), making its purpose unambiguous and distinguishing it from siblings.

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?

The description provides explicit guidance on when to use this tool ('Use this to find candidate files cheaply') and when to use alternatives ('Use tool_fuzzy_search_messages when searching message text instead of attachment metadata'), and directs the caller to tool_get_attachment for retrieving a specific attachment.

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

Deploy Server