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

Annotations already cover read-only/idempotent safety, so the description's added value is real: it discloses result semantics (`nothing` is true → say one line or nothing) and an interruption policy inside quiet hours keyed on vipWaiting. It does not mention cost/latency or how counts are scoped when inbox is empty, but the operational guidance it does give is substantial.

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 short sentences, purpose first, then usage, then output/quiet-hours rules. Every sentence carries an actionable instruction and nothing is repeated from annotations or schema.

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, so the description must convey the return payload; it names the key components (counts, VIPs, scams, snoozes, drafts, reminders) and two result flags (`nothing`, `vipWaiting`). That is enough to call and present it, though a slightly fuller picture of the response shape would close the remaining gap.

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 both `inbox` and `period` are already fully documented including defaults. The description only implicitly ties `period` to routines and does not add format or edge-case detail beyond the schema, so baseline 3 applies.

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 and resource ('One short summary of what needs the person') and enumerates its contents: counts, VIPs waiting, scams, snoozes due, stale drafts, reminders. That inventory makes it clearly distinct from siblings like list_messages, triage or get_triage_activity, which expose raw items rather than a curated brief.

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?

Gives two concrete triggers: the person asking what they missed, and morning/evening/weekly routines, which maps directly onto the `period` enum. It does not name an alternative for the raw-item case or state exclusions, so it stops short of full routing guidance.

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