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

Annotations already declare readOnly, destructive=false, openWorld and non-idempotent, so safety is covered. The description adds useful context beyond them: the GA4-connection prerequisite, the zero-cost nature, and the comparison-against-prior-window behavior, which the annotations do not convey.

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 compact sentences, front-loaded with the resource and the differentiating AI-referral feature. Slight density of parenthetical examples but no wasted prose.

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 naming return contents (sessions, share, growth per AI source, overall channel mix) and the connection prerequisite. Complete enough for an agent to call and interpret it, though it omits empty/missing-data behavior.

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%, so both parameters (site_id, days) are already documented with ranges and defaults. The description's mention of comparing 'the window to the prior one' adds mild context about what days controls, but nothing beyond the schema baseline.

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+resource ('GA4 traffic by source/channel') plus a distinctive capability (AI-assistant referral detection) that clearly separates it from siblings like get_ga_metrics or get_visibility_sources. An agent can select it without opening the schema.

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?

Gives a clear precondition ('Requires GA4 connected') and a cost signal ('Free read'), which tells the agent when the tool is usable and cheap to call. It does not name alternatives such as get_ga_metrics when that would be the better fit, so it stops short of explicit when-not guidance.

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