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

With no annotations provided, the description carries the full disclosure burden. It mentions 'formatted output' and 'human-readable' (useful for display expectations), but omits critical operational details: data freshness/retention (dates default to 8 days ago), pagination behavior, error handling for invalid domains, or whether results are cached. For a 15-parameter tool with complex filtering capabilities, this is insufficient behavioral context.

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?

Two sentences, zero redundancy. First sentence defines the operation and output format; second describes the ranking behavior. However, given the tool's complexity (15 parameters), the description may be overly terse—sacrificing completeness for brevity. No filler words, but could front-load more salient differentiators from sibling tools.

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 tool with 15 parameters spanning pagination (pageNumber, pageSize), date ranges (daysBack, daysTo), multi-dimensional filtering (country, deviceType, pageGroup), and statistical measures, the description is inadequate. It makes no mention of temporal data aggregation, pagination limits, or the fact that it supports filtering across multiple dimensions simultaneously. Without an output schema, the description should have described the return structure or at least acknowledged the filtering capabilities.

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%, so the schema adequately documents all 15 parameters including date formats, metric options (LCP, INP, etc.), and ranking criteria. The description adds semantic context by linking these to 'Core Web Vitals metrics' and mentions 'ranked by performance or popularity,' but doesn't expand on parameter interactions (e.g., how 'page' filtering interacts with 'grouped') or provide syntax examples beyond the schema. Baseline 3 is appropriate given schema completeness.

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?

Clear verb ('Gets') and resource ('page-by-page performance breakdown'). Mentions 'Core Web Vitals metrics' and 'ranked by performance or popularity' which adds specificity. However, it doesn't distinguish from siblings like 'get_page_performance_breakdown_by_browser' or 'get_page_performance_breakdown_by_country'—leaving ambiguity about when to use this aggregate version versus the dimension-specific ones.

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?

No explicit guidance on when to use this tool versus alternatives like the domain overview or browser/country-specific breakdowns. While it mentions that results can be ranked by performance or popularity, it doesn't clarify prerequisites (e.g., needing a valid domain) or suggest which metric/filter combinations are most useful for common use cases.

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