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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context by defining the recency window and enumerating the content of the response, which helps an agent recognize this as a low-cost snapshot rather than a full report. It stops short of stating the exact window length or any result caps.

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?

One sentence, front-loaded with the scoping constraint ("last few minutes") followed by the returned dimensions. Every clause carries information and there is no filler.

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 work of telling the agent what comes back, and it covers that well for a one-parameter read tool. The main residual gap is the imprecision of "last few minutes" and no mention of result limits, but nothing essential to invoking it correctly 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 site_id parameter already documents that a name, slug or domain resolves in addition to the ID from list_sites. The description adds nothing about the parameter, so the baseline 3 applies.

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 names a specific resource and scope: current visitors, described as "who is on the site in the last few minutes," and enumerates the dimensions returned (active visits, top pages, countries, devices, latest events). This clearly separates it from historical siblings like get_timeseries or list_visits, though it never names an alternative directly.

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 "last few minutes" framing implies this is the tool for live monitoring rather than historical analysis, which is enough for an agent to infer intent. However, there is no explicit when-to-use statement, no excluded cases, and no pointer to a sibling for longer ranges.

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