Skip to main content
Glama
macos-mail-mcp

macos-mail-mcp

save_all_attachments

Saves all downloaded attachments from a specified Mail message to a chosen directory, creating the destination folder recursively before contacting Mail.

Instructions

Save all downloaded attachments from a message to disk. Creates the destination directory recursively before contacting Mail.

Input Schema

NameRequiredDescriptionDefault
savePathNoThe directory path to save the attachments to (default ~/Downloads)~/Downloads
messageIdYesThe numeric ID of the message
accountNameYesThe name of the account containing the mailbox
mailboxNameYesThe name of the mailbox containing the message

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv1.3.2
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / messageId / maximum
      Added value: +9007199254740991
    • addedInput schema / properties / messageId / minimum
      Added value: +-9007199254740991
  2. First observedv1.2.0

TDQS

B3.2/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full burden. It usefully discloses that the destination directory is created recursively and that this happens before contacting Mail, but it says nothing about overwrite behavior for files that already exist, what happens when a message has no attachments, or permission/error conditions.

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?

Two short sentences, front-loaded with the action and free of filler. The ordering detail ('before contacting Mail') is slightly niche but does convey real behavior about partial failure, so it earns its place.

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?

It states the core action, the destination handling, and the mutation footprint for a 4-parameter tool with full schema coverage. The gaps are return values (output schema absent) and overwrite/duplicate handling, which would round out a write tool with 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 coverage is 100%, and the schema already documents savePath with its default. The 'creates the destination directory recursively' clause adds real meaning by telling the agent that savePath need not already exist, but that is the only genuine addition beyond the schema.

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 gives a specific verb and resource: 'Save all downloaded attachments from a message to disk.' The word 'all' implicitly separates it from the singular save_attachment sibling, but it never names that alternative explicitly, so an agent must infer the distinction.

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 at all. With siblings list_attachments, save_attachment, and read_attachment in the lineup, the definition should say when bulk-saving beats enumerating or saving one attachment, and it does not.

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