cf_web_analytics

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds value by explaining the edge-measured traffic nature and how it complements GA4, providing behavioral context beyond the annotations.

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 very concise—three short sentences that are well-structured. The first sentence states the tool's purpose, the second explains the two usage modes, and the third provides additional context and limitation. No superfluous information.

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 lack of an output schema, the description could be more explicit about return data structure (e.g., 'returns site details including metrics'). However, the tool is simple and the domain is well-known, making it adequate for an experienced agent. The openWorldHint annotation also helps set 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?

The sole parameter host_or_tag is fully described in the schema. The description adds parsing logic (hostname vs. site_tag) that goes beyond the schema description, giving clear semantic meaning.

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 is for Cloudflare Web Analytics (edge RUM), specifies two modes of operation (listing all sites or retrieving a site's detail), and distinguishes it from GA4 by mentioning edge measurement. The purpose is specific and unambiguous.

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 explicitly explains when to use the tool without arguments (list all sites) and with the host_or_tag parameter (get one site's detail). It also notes that create/delete operations are intentionally not exposed, guiding the agent away from writing operations.

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