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

Annotations already declare readOnly, idempotent and openWorld, so safety is covered. The description adds real behavioral value: results are returned side by side for comparability, and a site that blocks automated readers is reported as unreadable rather than failing silently.

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?

Three short sentences, front-loaded with the operation and scope. 'So a score means something' is slightly promotional but functions as the rationale for the comparison, so little is wasted.

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 low-parameter, read-only tool with full annotation coverage and a 100%-documented schema, the description is nearly sufficient: it conveys the comparison output shape and the unreadable-site edge case. No output schema exists, but the return is described in prose.

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% (urls and lang both documented, including the en default), so the schema carries the parameter burden. The description reinforces the 2-to-4 site constraint on urls but adds no format or syntax detail beyond it.

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 ('Runs the same AI-visibility scoring on two to four sites and returns them side by side'), with the multi-site scope making it distinguishable from single-site siblings like audit_site. It doesn't name a sibling directly, but the comparison purpose is 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?

'Use it to see where a site is losing answers to a rival, area by area' gives a clear use context. However, it offers no explicit when-not guidance or routing against near-neighbors such as audit_site or check_rival, leaving the agent to infer the boundary.

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