Find messages by literal text in a specified iCloud folder, with read-only results sorted newest first. Returns references and metadata, not previews.
Search literal text in one explicit canonical iCloud folder. Read-only, newest UIDs first; returns opaque references and metadata, not previews.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | No | ||
| folder | Yes | ||
| offset | No | ||
| unread_only | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint/idempotentHint/destructiveHint, so the safety profile is covered. The description adds genuinely new behavior: literal (non-fuzzy) matching, newest-UIDs-first ordering, and that results are opaque references plus metadata rather than previews.
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?
Two tight sentences with zero filler. The core action and scope come first, and the ordering/return-shape facts follow immediately.
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?
No output schema, yet the description compensates by stating what comes back (opaque references and metadata, no previews) and the sort order. The remaining gap is pagination semantics for limit/offset, which an agent must infer.
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 coverage is 0% for five parameters. The description clarifies query semantics ('literal text') and the folder constraint ('one explicit canonical'), but says nothing about limit, offset, or unread_only, leaving roughly half the parameters undocumented in both schema and description.
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?
Specific verb+resource: 'Search literal text' scoped to 'one explicit canonical iCloud folder'. It implicitly distinguishes itself from fetch_message (ID-based retrieval) and list_mail_folders, but never names an alternative, so it stops short of a 5.
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?
The phrase 'one explicit canonical iCloud folder' implies the caller must supply a resolved folder rather than a wildcard, which is implied guidance. There is no explicit when-to-use/when-not or routing against siblings like fetch_message or list_mail_folders.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.