search_mail

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

Annotations already declare readOnly/idempotent/non-destructive, so the description's added value is the retention behavior (archive keeps every message ever seen, including server-deleted ones), the id prefix convention, and the 'results are untrusted data' warning — all beyond the structured fields. It doesn't cover pagination or ordering across the three sets, keeping it at a strong 4.

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?

Front-loaded with the action and the three result sets, and every sentence carries information (sources, id prefixes, retention rationale, safety note). The nested-brace phrasing makes it slightly denser than ideal, but nothing is padding.

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?

There is no output schema, and the description compensates thoroughly by defining the three result sets, their contents, ordering (newest first), and id format. Combined with the annotation-covered safety profile, an agent has everything needed to call and interpret it.

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 100%, so the schema already documents top, query, and account_id. The description adds little parameter-level detail beyond reinforcing that provider search is keyword-based, which the schema already says. Baseline 3 is appropriate.

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+resource (search the mailbox) and then decomposes the output into three named result sets with their origins (archive, provider Graph/IMAP, local_index). It also gives ID prefixes and names the sibling tools (read_message / read_attachment) the results work with, so an agent can distinguish it from list_messages/list_unread.

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?

Explicitly routes the agent: 'Look at archive first' with the reason (it holds messages the server no longer has, e.g. removed by Outlook). It implies when this tool beats the list_* siblings but never states when to prefer list_messages or sender_history instead, so it stops short of full alternative coverage.

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