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

With no annotations, the description carries the full burden, and it does disclose meaningful behavior: the scope is the entire recorded history with no filtering, timestamps are normalized to Asia/Shanghai, and the tool explicitly does not predict. It omits any note on cost, caching, or data freshness, which is the remaining gap for a read-only aggregate.

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?

A single dense sentence that front-loads the scope ('full recorded history'), lists the returned metrics compactly, and closes with the key constraint ('History only — not a prediction'). No filler and nothing buried.

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?

For a parameterless, annotation-free tool with no output schema, the description must explain the return shape — and it does so by naming every computed metric. Combined with the scope and timezone disclosure, an agent has everything needed to call it and interpret results.

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?

The tool takes zero parameters, so the baseline is 4. The description correctly communicates that no filtering is possible by emphasizing 'over the full recorded history', which prevents an agent from hunting for a date-range argument that does not exist.

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 uses a specific verb+resource ('Cadence statistics over the full recorded history') and enumerates the exact metrics returned: total verified resets, 30/90-day counts, gap statistics (avg/median/min/max), monthly counts, and announcement-time distribution. This clearly differentiates it as the aggregate-statistics endpoint, though it never names the siblings (get_latest_reset, list_reset_events) that an agent would choose between.

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 rather than stated: 'History only — not a prediction' is an exclusion that tells the agent this is not a forecasting tool, but there is no explicit guidance on when to pick it over get_latest_reset or list_reset_events. The agent must infer that aggregate cadence questions belong here while single-event questions belong to the siblings.

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