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

Annotations already declare readOnly/idempotent/closed-world, and the description adds real operational context: the 90-day clicks window, that page fields come from the latest completed crawl, and the important caveat that each finding stores only up to 50 example URLs so a page can be affected without being listed. That caveat is exactly the kind of behavior an agent cannot infer from 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?

A single very long run-on sentence with nested clauses; the core purpose is front-loaded, but the enumeration of status code, title, H1, meta description, findings and sitemap blocks makes it hard to scan. Little is wasted, but structure could be improved with a returned-data breakdown.

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?

With no output schema and no annotations covering return shape, the description does the heavy lifting by naming the page fields, the findings relationship and the sitemap block. It is close to complete for a read-only listing tool, missing only pagination/default-limit behavior and a pointer to alternatives.

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%, so the schema already documents sort, limit and site_id fully. The description adds only the 'Google clicks over 90 days' framing that implicitly explains the default clicks sort, but nothing about limit or the issues sort beyond what the schema states.

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?

Opens with a specific verb+resource ('List the pages of a website') and enumerates the returned fields, so an agent knows exactly what the tool produces. It never names a sibling (e.g. list_issues) as the alternative for findings-only queries, which keeps it short of a 5.

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?

There is no explicit when-to-use / when-not guidance and no mention of alternatives such as list_issues for finding-level data or get_site_metrics for aggregate metrics. Usage must be inferred from the field list alone.

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