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

Annotations already declare readOnlyHint=true, openWorldHint=true, destructiveHint=false, so the safety profile is covered and the bar is lower. The description usefully adds that results are summed over the window, sorted by clicks, and refreshed weekly — genuine behavioral context. However, it says nothing about pagination or row limits interacting with the aggregation.

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 the primary resource and output metrics front-loaded before the mode-switch caveat and the freshness note. Dense and largely waste-free, though the metric list and mode-switch could have been split for faster scanning.

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 read-only reporting tool with no output schema, the description does the important work of naming the returned fields and their aggregation/sort semantics, so an agent can anticipate the shape of the response. Data freshness is also covered. Minor gaps remain around result size and how the query mode changes the returned fields.

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 every parameter (limit, query, endDate, siteUrl, startDate) is already documented in the schema, including query's mode-switching behavior and siteUrl's multi-site condition. The description restates the query mode rather than adding syntax, formatting, or edge-case detail beyond the schema, so the baseline of 3 applies.

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?

States a specific verb+resource — the Bing search queries that drive impressions to the site — and enumerates the returned metrics (clicks, impressions, CTR, average position). It is clear, but it never names its near-twin sibling bing_top_pages, so the agent must infer the distinction from the dual-mode sentence rather than being routed explicitly.

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 gives a concrete conditional: 'Pass `query` to instead see which of the site's pages rank for that one search,' which tells the agent when to switch modes. It also notes the weekly update cadence so the agent knows not to expect real-time data. It stops short of stating when not to use the tool or naming an explicit alternative tool.

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