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

Goes well beyond the annotations: it explains data staleness (figures come from the prior check when last_error is set), defines not_enough_data as normal for small sites rather than a failure, explains checked=false and checks_enabled=false conditions, and confirms 'never calls Google', reinforcing openWorldHint=false. This is exactly the context annotations cannot carry.

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 purpose is front-loaded and nearly every clause carries real semantics, but the whole definition is one long comma- and semicolon-chained sentence that is hard to parse and is heavy for a tool with a single optional parameter. Structure (paragraph or bullets separating what-is-returned from status semantics) would earn the remaining points.

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, the description carries the full burden of describing return values and does so field by field, including units, thresholds and the meaning of every status flag. Nothing an agent needs in order to call it and interpret the result 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?

Only one parameter, whose schema description already covers it at 100% coverage ('Sites to read. Omit for every site.'). The description restates the default rather than adding new meaning, and does not mention the 100-item maxItems cap, so this is baseline territory.

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 names a concrete verb/resource pair (reads each chosen site's home page speed from a weekly Google check) and enumerates exactly what is returned: mobile and desktop lab scores out of 100, lab LCP/CLS/TBT/FCP/SI, and 28-day Core Web Vitals. This is clearly distinguishable from siblings like uptime_status or site_health.

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?

Usage is only implied: it is a read-only status read over one or more sites, with site_ids optional and defaulting to every site. There is no explicit statement of when to prefer this over recipe__site_report, recipe__run_site_health or the performance-oriented sibling tools, and no stated prerequisites or exclusions.

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