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

The description discloses all relevant behavioral traits: return fields (sessions, bounce rate with reliability caveat, revenue, last_cited_at with timezone), default limits per mode, scope (clicked citations only), and that methodology is fixed in code. The readOnlyHint annotation is consistent with the read-only nature described. No contradictions.

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 front-loaded with the primary purpose and then details each mode. It is dense but efficient; every sentence adds value. A slight reduction in length or use of bullet points could improve scannability, but it remains well-structured and avoids fluff.

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?

Given the tool's complexity (two modes, four parameters, output schema present), the description covers all necessary aspects: input parameters, return values for each mode, methodology notes, timezone info, and scope. The presence of an output schema does not reduce the need for explanation, and the description exceeds expectations.

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 0% schema description coverage, the description fully compensates by explaining each parameter: mode (enum values and defaults), limit (defaults per mode), period (string shortcuts and integer range), and site_id (optional when OAuth). It also explains the format of the last_cited_at field in the output, aiding understanding of the data.

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 the tool returns AI-assistant traffic for a given period, with two distinct modes ('referred' and 'gaps') that are each explained in detail. It lists the specific AI sources (ChatGPT, Claude, etc.) and contrasts with GA4/GSC, making the purpose unambiguous and distinguished from general analytics tools.

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 explains when to use each mode: 'referred' for listing landing pages with AI traffic and 'gaps' for identifying missed opportunities. It also notes that the view cannot be produced by GA4/GSC, implying it's the only tool for this purpose. However, it does not explicitly compare to sibling tools like get_breakdown or get_keyword_performance, leaving some ambiguity about alternatives.

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