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

Annotations already cover safety (readOnlyHint, idempotentHint, closed-world), but the description adds genuinely new behavior: the 5-minute check cadence and the hard cap of at most 200 domains per call. Those are real operational constraints the agent cannot infer from the schema or 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?

Two dense sentences, front-loaded with the scale of the resource and immediately followed by the no-arg vs filtered behavior. Every clause carries information an agent would otherwise have to guess.

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 output schema, the description does the correct work of describing both return shapes (category list with counts, domain lists). Minor omissions remain, such as whether query and category can be combined in one call, but nothing critical is missing for correct 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 100% and both parameters are well documented there, so the description adds little per-parameter meaning. Its only contribution is the 200-result cap, which relates to result size rather than argument syntax.

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?

States a specific verb and resource ('634 sites checked every 5 minutes, grouped in 17 categories') and gives the result shape, so the agent knows it is listing monitored sites rather than outages or certs. It never names a sibling to distinguish itself explicitly, which is the only gap.

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?

Explicitly explains the two invocation modes: no arguments yields the category list with counts, and filtering by category or text query yields domains. That is clear operational context, though it does not say when to prefer this over check_site or site_history.

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