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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely non-obvious behavioral context: the data is cookieless, retention is limited by plan ('for the days the plan keeps'), some metrics are paid-plan-only, and taps outside the UK are excluded (taps_not_counted). These are real caveats that affect interpretation of results.

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 sentences, front-loaded with the headline result and then the metric inventory and the caveats. The nested parenthetical is dense but every element (metrics, plan gating, UK exclusion) carries information. Slightly heavy in one clause, so a 4 rather than a 5.

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 the description need not explain return values; it instead spends its budget on data limitations and plan gating, which is the right choice for a 4-param read tool. Minor gap: it never mentions the required `site` parameter or the default 7-day window, leaving those entirely to the schema.

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?

With 75% schema coverage the schema documents days, recent, and compare. The description still adds meaning by tying the `days` window to plan retention limits and by marking the extra metrics (and implicitly `compare`) as paid-plan features. It does not restate the `site` or `recent` semantics, which the schema already handles.

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 ('Returns') plus resource ('cookieless visitor numbers') with an explicit enumeration of the metrics returned (views, visitors, contacts, and paid-plan extras). It clearly describes the output domain. It does not explicitly differentiate from the closest sibling, find_visitor_records, so it stops short of a 5.

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 description never states when to use this tool versus alternatives such as find_visitor_records or get_activity, nor any prerequisites. The only contextual hint is the parenthetical retention phrase 'for the days the plan keeps', which implies a data-availability constraint but is not framed as usage guidance.

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