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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), and the description adds substantive operational context beyond them: no outbound request to the target, ~15-minute scheduling cadence, a 35-minute staleness threshold, and a 12-sample cap. It also scopes the authority of the data ('not official or global').

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?

Five short sentences, front-loaded with the core action, then the non-probe caveat, then the timing/staleness facts. No filler; each sentence carries a distinct operational fact.

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?

An output schema exists, so return-shape explanation is unnecessary, and the description still flags that samples, freshness, scope, and the status link come back. For a one-parameter cached-read tool, nothing an agent needs before calling is missing.

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 single enum parameter is already documented as a service ID drawn from list_monitored_services. The description only adds the word 'curated,' which mildly reinforces the fixed enum set but contributes no new syntax or selection guidance beyond 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?

Specific verb and resource: reads the latest scheduled homepage observation plus up to 12 recent samples for a curated service. It explicitly states what it does NOT do ('Does not make a new request to the target website'), which separates it cleanly from check_website/check_dns siblings.

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 'no new probe' framing plus the freshness/staleness numbers tell the agent when cached data is acceptable versus when a live check is needed. 'Not an official or global outage report' excludes the outage-report use case, implicitly pointing at get_provider_incidents, though no sibling is named outright.

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