Search Apple Mail mailboxes by subject or sender. Read-only results return bounded metadata without bodies, so you can locate messages without loading full content.
Read-only: search a mailbox by subject or sender; returns bounded metadata without bodies.
| Name | Required | Description | Default |
|---|---|---|---|
| field | No | subject | |
| limit | No | ||
| query | Yes | ||
| account | No | iCloud | |
| mailbox | No | INBOX |
Changes observed during successful MCP inspections.
v3.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, yet the description adds real context: results are bounded and carry metadata only, no message bodies. That tells the agent what it will and will not receive, which the annotations do not.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single front-loaded sentence that covers scope, method, and return shape with no filler. Every clause earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The lack of an output schema is partly offset by the description stating the return shape (bounded metadata, no bodies). However, for a 5-parameter tool with zero schema descriptions, the missing account/mailbox/limit semantics leave an agent under-informed about how to call it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0% across 5 parameters. The description only conveys the `field` semantics (subject/sender) and implies `query`; the `account`, `mailbox`, and `limit` parameters, including their defaults and the limit ceiling, are undocumented in both schema and description, so the compensation is partial at best.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (search) and resource (mailbox) plus the searchable fields (subject or sender), which maps directly to the `field` enum and separates it from list/get siblings. It stops short of naming an alternative tool explicitly, so it is clear but not sibling-differentiating in the strongest sense.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is only implied: an agent can infer 'search' rather than 'list' (apple_mail_list) or 'fetch one' (apple_mail_get), but there is no explicit when-to-use, when-not-to-use, or named alternative. Adequate but leaves routing to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.