sender_stats

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

With no annotations at all, the description carries the full disclosure burden. It does disclose valuable behavior: it scans only the newest `scan` messages with a lean field set and issues one request per 1000, which signals cost/latency. It never states that the operation is read-only, what permissions are needed, or that results are capped at top_senders, which is the main omission.

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 return shape is front-loaded, followed by the usage cue and then per-parameter notes; every sentence carries information. The fragmentary third sentence ('The first call for any cleanup...') and slightly awkward line wrapping keep it from being maximally clean.

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 annotations and no output schema, the description still conveys what the tool returns field-by-field and how much mail it scans, which is enough to call it correctly. The gaps are the undocumented top_senders cap and any statement of read-only safety, though neither would cause a wrong invocation.

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 description coverage is 0%, so the description must compensate. It adds real meaning for `scan` (default 1000, max 5000 – the max is not in the schema) and `days` ('count only mail from the last N days'), and implies `folder`. However `top_senders`, which controls output size at 25 by default, is never mentioned, leaving one of four parameters undocumented everywhere.

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 opening sentence gives a specific verb (rank) and resource (senders in a folder) and even enumerates the per-sender fields produced (message count, unread count, date range, sample_message_id, looks_automated). It implicitly positions itself ahead of the other cleanup tools, but never names a sibling such as find_bulk_mail or messages_from_sender, so differentiation is positional rather than explicit.

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?

'The first call for any cleanup or "who emails me most" question' gives a concrete triggering scenario and implies downstream tools follow. There are no explicit when-not conditions or named alternatives to route away from, so it stops short of full guidance.

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