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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description only needs to add context beyond that. It adds that data comes from the Bing AI Performance CSV uploaded in the dashboard, which is useful context for data freshness and source. However, it does not disclose pagination, rate limits, or behavior when no CSV data exists, so it provides modest additional transparency.

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 with no filler. The first sentence front-loads the core purpose, and the second adds a valuable data-source note. Every sentence earns its place, though the structure could be tightened with an explicit verb at the start.

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 simple one-parameter read-only tool, the description covers the output contents (frequency, pages, questions) and the data source, which gives an agent a reasonable idea of the result. However, there is no output schema and the description doesn't mention response format, empty-data behavior, or potential caveats, leaving some gaps for a complete call.

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%, with the single `site` parameter fully documented including accepted formats and a hint to call list_sites if unsure. The description itself references 'this site' but does not add any new meaning beyond what the schema already provides, so the baseline of 3 is appropriate.

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 identifies a specific resource ('this site'), a specific metric (how often Microsoft Copilot cited it in AI answers), and the data dimensions (frequency, pages, questions). This clearly differentiates it from siblings like bing_performance or search_performance, which cover broader areas. It lacks an explicit verb like 'get' or 'list,' but the phrasing clearly implies a read/report operation.

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 instead of related siblings such as bing_performance or search_performance, and it names no alternatives or exclusions. The schema's 'Call list_sites if unsure' is only a fallback for site format validation, not a usage guideline for tool selection.

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