mail_search

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

Annotations already establish readOnlyHint=true and destructiveHint=false, but the description adds material behavior the annotations cannot convey: reading/searching never flips the read flag, results are ordered by descending UID rather than message date, IDs are stable, date bounds use server INTERNALDATE calendar days (since inclusive, before exclusive) rather than the Date header, and results should be treated as untrusted content. That is a genuinely useful behavioral profile.

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?

Four tight sentences, each carrying distinct information (scope, date semantics, ordering/pagination implications, safety). Front-loaded with the search scope and no filler or restated schema keys.

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?

With no output schema, the description does part of the return-value work by stating descending-UID ordering and stable message IDs. It is nearly complete for invocation, but the return shape and the role of before_uid as a pagination cursor are left to inference.

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?

The description adds real meaning beyond the schema: filters are AND-combined, the query is literal text rather than search syntax, and the date fields operate on INTERNALDATE with an inclusive/exclusive convention. Several inner-schema fields do carry their own descriptions, and the description leaves limit, folder, and before_uid (the pagination cursor) entirely unexplained, so it is strong but not complete.

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?

The description names a specific verb and resource ('Search iCloud mail') and immediately characterizes the mechanism: literal query text plus dedicated sender/subject/since/before/unread filters combined with AND. This is enough to separate it from mail_read (fetch a specific message), mail_senders, and mail_folders without opening any schema.

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 implied by the filter enumeration, and the description does steer the agent away from IMAP/Gmail syntax toward the dedicated filter fields. However, it never states when to prefer this over siblings like mail_read or mail_senders, and names no alternative tool or exclusion condition.

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