ai_referral_overview

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds valuable behavioral context: the undercount disclaimer (~70% land as Direct) and the fact that AI-Overview clicks are excluded. This goes beyond what annotations provide but does not cover all potential edge cases.

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?

The description is compact at two sentences with a semicolon, covering all necessary points without fluff. It is front-loaded with the main purpose and ends with an important caveat. Minor improvement: could use structured bullets for the two components, but current structure is efficient.

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?

The description covers purpose, prerequisites, and limitations well, but lacks any mention of return values or output format. Since the tool has no output schema, the description should at least hint at what the agent can expect (e.g., a JSON object with referral stats and crawl status). Parameters and annotations are well-covered, but output 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% with parameter descriptions, but the tool description adds default behaviors (days defaults to 28, site_url defaults from GSC default site, property_id defaults to configured property) and functional grouping (days for GA4 referral, site_url for crawl coverage). This significantly enhances meaning beyond the raw schema.

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 clearly states it provides a 'First-party view of AI traffic' with two specific components: AI referral sessions via GA4 and AI-crawler coverage via robots.txt. It names specific AI apps and bots, making the resource scope explicit. This verb+resource+scope structure distinguishes it from sibling tools like robots_ai_posture or ga4_organic_search_overview.

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 provides clear prerequisites (GA4 property for referral, site_url for crawl coverage) and defaults for parameters. It includes an explicit honest bound about undercounting and AI-Overview clicks counting as Organic. However, it does not explicitly state when not to use this tool or mention alternative tools for similar tasks.

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