Skip to main content
Glama
Sign In
Timbre

Timbre

by alejandrosml
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Local

create_rule

Destructive

Creates Apple Mail rules that filter incoming messages by conditions and apply actions like move, flag, or trash, with a 90-day preview before user confirmation.

Instructions

Make a rule in Mail for mail as it arrives: conditions (from, to, subject, text, a header…) and actions (move, copy, mark read, flag, trash, stop). It is first tried on the last 90 days (preview: true only tries it). Then a window on the Mac shows the user the rule and what it would have taken: only their click makes it. Presets: mute_thread (a conversation's new mail read and archived), block_sender. Forwarding, replies and scripts stay in Mail's own settings.

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": "create_rule"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoThe message a preset is about.
allNotrue (default): every condition must hold; false: any one.
nameNoThe rule's name, as Mail will show it.
presetNoA ready-made rule: "mute_thread" (id: new mail in that conversation is marked read and archived) or "block_sender" (id or address: that sender's mail goes to the trash).
actionsNo
addressNoFor block_sender: the address to block.
previewNotrue: only try the rule on the last 90 days; nothing is made.
conditionsNoWhat incoming mail the rule takes (1-10 conditions).

Output Schema

NameRequiredDescriptionDefault
noteYes
ruleNo
trialNo
statusYespreview, awaiting_approval, created, cancelled, enabled, disabled or deleted.
undo_tokenNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.7.2

TDQS

A4.5/5.0
Behavior5/5

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

Beyond destructiveHint=true and idempotentHint=false, the description discloses the critical confirmation loop: a Mac window shows the user the rule and what it would have taken, and "only their click makes it." It also explains preview=true as a non-committal dry run over 90 days and clarifies that block_sender trashes mail — behavior an agent cannot infer from annotations alone.

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 text is compact and front-loads purpose before mechanics, with no filler sentences. The telegraphic, run-on style (parenthetical asides stacked mid-sentence) makes it slightly harder to parse than a cleanly segmented version, but every clause carries information.

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?

With an output schema present, return values need not be explained, and the annotations carry the safety profile. The description still covers the confirmation workflow, preview semantics, presets, and explicit exclusions for a fairly complex 8-parameter mutation tool, leaving only minor gaps such as the requirement that presets pair with id or address.

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 already 88%, so the baseline is 3, but the description adds meaning on top: preview is framed as "only tries it," and the two presets are expanded with their concrete semantics (mute_thread marks new conversation mail read and archives; block_sender trashes the sender's mail). It reinforces the condition/action vocabulary without restating syntax the schema already gives.

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 opening sentence names a specific verb and resource ("Make a rule in Mail") and scopes it to incoming mail, then enumerates the condition fields (from, to, subject, text, header) and action types (move, copy, mark read, flag, trash, stop). An agent can distinguish this creation tool from siblings like change_rule and list_rules without inspecting schemas.

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

Usage Guidelines4/5

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

The description gives clear operating context: it is first tried on the last 90 days, and presets mute_thread and block_sender are named with their effects. It also draws an explicit boundary — forwarding, replies and scripts "stay in Mail's own settings" — so the agent knows what this tool will not do. It does not say when to prefer change_rule over creating a new rule, which keeps it short of a 5.

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

Deploy Server

Other Tools