get_statistics

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds that it is a read-only analytics roll-up from a single search_messages pass and explains the scan_limit truncation behavior, providing useful context beyond the annotations.

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 moderately sized but well-structured, with each sentence adding meaningful information. No unnecessary repetition or fluff.

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?

The tool has 8 parameters and an output schema. The description covers the main behavioral aspects, including the window_fully_covered indicator, which helps the agent interpret results. Given the existence of an output schema, it does not need to detail return values.

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%, but the description adds value by explaining defaults (e.g., received_within_hours=720), the meaning of scan_limit, and the window_fully_covered flag, which is not in the schema.

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 clearly states it aggregates inbox statistics (message volume, read/unread/flagged counts, read ratio, top senders) over a mailbox and time window, and distinguishes itself from sibling tool 'list_mailboxes' which provides per-folder unread counts.

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?

It explains the default window (last ~30 days) and how to set explicit ranges via date_from/date_to. It also notes the scan_limit behavior and the window_fully_covered indicator, guiding the agent on when the results are a sample rather than a full scan. However, it does not explicitly state when not to use this tool.

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