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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds real behavioral context the annotations don't: the figures come 'from the source,' crawler_visits is a 'rolling window,' and results carry an 'at timestamp' indicating freshness — all relevant to interpreting the values.

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 front-loaded sentence with no filler; the field enumeration is justified because no output schema exists to carry it. Phrasing like 'with an at timestamp' is slightly awkward but still efficient.

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 input parameters and no output schema, the description carries the return-value burden, and it does so by naming every returned field plus the freshness marker. The only gap is the lack of routing guidance relative to sibling data tools.

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 per the rubric the baseline is 4. Nothing in the description is needed on the input side and nothing is missing.

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 — the self-reported CrawlCheck metrics — and enumerates exactly which figures are returned, so an agent can tell what it gets. It never uses an explicit verb (no 'returns'/'reads'), and it does not differentiate itself from data-ish siblings like corpus_state or telemetry.

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?

There is no when-to-use or when-not-to-use guidance, and no alternative tool is named. The agent must infer from the sibling list alone whether this public-stats tool or corpus_state/telemetry is the right call.

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