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 real value with the 5-minute recency definition and the shape of the returned data, but says nothing about result caps (how many concurrent visitors are returned), latency, or sampling, which matter for a live-data endpoint.

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 front-loaded sentence that defines the metric window first and then the payload. Every clause carries information, and the parentheticals are used to enumerate fields rather than to hedge.

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 read-only, single-parameter tool with no output schema, the description supplies the temporal definition and the return content, which is the right amount of coverage. The only real omission is any statement about result limits or ordering for the returned visitor list.

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 the single website parameter is already documented with an example ('example.com') plus a pointer to list_websites. The description adds no further meaning about the parameter, which is the expected baseline when the schema does the work.

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: visitors on the site right now, with the recency window pinned down as 'seen in the last 5 minutes', and it enumerates the returned dimensions (page, source, location, device, activity). This distinguishes it from historical siblings like get_overview and get_timeseries, though no sibling is named explicitly.

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 context is clear: this is the real-time tool, selected when the question is about who is on the site at this moment rather than over a date range. It stops short of explicit exclusions or naming the alternative to use for historical traffic, so an agent must infer the boundary itself.

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