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

Beyond the annotations (readOnly, idempotent, openWorld), the description discloses several non-obvious traits: reading marks nothing as read, the 2,000-message per-folder truncation and that the result reports it, UTC timestamps, and that classification is header-based, never content-based, with a `reason` per automatic entry. These are exactly the behaviors an agent needs and cannot get from the structured fields.

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?

The description is dense but front-loaded: the core result shape comes first, then classification rules, then window/cap constraints. Nearly every clause carries information, though the sentence about reply detection ('each by a message addressed to them in Sent, or by the answered flag') is harder to parse than it needs to be.

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 carries the full burden of describing return shape and it does so thoroughly: conversation fields, preview, counts, unread counts, reply status, separately listed automatic mail with sender/subject/reason, and the `totals` object. An agent knows what it will get back.

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% and the schema already documents hours, limit, since (with offset and the 'give this or hours, not both' rule) and mailboxes. The description adds only the UTC note and confirms that limit doesn't affect totals, so 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?

The description states a specific resource and scope ('what arrived in a recent window, grouped into conversations, in one call') and describes behaviors (conversation grouping, separating newsletters/automatic mail, reply status) that no sibling like list_emails or search_emails offers. An agent can tell it apart from read_thread and owed_replies without opening a 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 'in one call' and the grouped-summary framing, but the description never explicitly says when to prefer this over list_emails, search_emails, owed_replies, or waiting_on. No exclusions or alternative-routing guidance is given.

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