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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds the domain scope of the data (AI platforms such as ChatGPT, Claude, Perplexity) but says nothing about attribution logic, aggregation granularity, or behavior when no AI referrals exist. Adequate but not rich.

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?

A single front-loaded sentence with zero filler; the resource scope and the concrete platform examples are the only content and both earn their place.

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 2-parameter read-only tool with full schema coverage the core is covered, but there is no output schema, so the description could usefully say what metrics/shape come back (sessions, referrers, per-platform breakdown). Without that, an agent knows what to call but not what it will receive.

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% — both 'days' (default 30) and 'projectId' (UUID) are documented in the schema. The description adds no meaning beyond the schema, e.g., the timezone or whether 'days' is calendar or rolling; baseline 3 applies since the schema carries the load.

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 ('get analytics for traffic referred from AI platforms') and enumerates the source platforms, so the agent knows exactly what data class this returns. It does not, however, distinguish itself from near-siblings like get_site_analytics or get_search_performance, which cover overlapping analytics territory.

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 is only implied: an agent can infer this is for AI-referred traffic specifically, but the description gives no when-to-use condition, no prerequisite (e.g., analytics must be connected), and never names get_site_analytics or get_search_performance as the alternative for non-AI traffic.

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