content_refresh_candidates

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

With no annotations provided, the description carries the full burden of disclosing behavior. It states the tool ranks pages but does not reveal whether it is read-only, whether authentication to both GSC and GA4 is required, how the data is combined, or any limitations such as rate limits or data freshness. This is a significant gap for a tool that likely performs multi-source analysis.

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 a single, succinct sentence that clearly states the tool's core function without any filler. It is front-loaded with the action and purpose, making it easy to parse. No unnecessary words or redundant details.

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 that combines GSC and GA4 data to rank pages for refresh, the description is overly minimal. It does not explain what 'opportunity' means, which engagement metrics are used, how the ranking is computed, or what the output format is. There is no output schema, so the description alone must clarify expected results, but it does not. The tool's complexity demands more detail than provided.

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 80%, with startDate, endDate, siteUrl, and property having descriptions in the schema, and rowLimit lacking description. The tool description adds no parameter-specific information beyond the schema. Since the schema does most of the documentation, the baseline of 3 is appropriate; the description does not compensate for the undocumented rowLimit parameter.

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 action (rank), the resource (pages), and the criteria (GSC opportunity and GA4 engagement), making the purpose distinct from pure GSC or GA4 reporting tools. It implicitly differentiates from siblings like gsc_top_pages or ga4_top_pages by combining both data sources, but does not explicitly name alternatives, so it stops 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?

The description provides no guidance on when to use this tool versus its many siblings (e.g., seo_opportunity_report, find_pages_with_clicks_but_low_engagement). It does not state prerequisites, such as whether both siteUrl and property are required, or when a user should choose this over a more specific report. The context is entirely implied by the name and brief description.

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