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

Annotations already flag this as read-only and non-destructive; the description adds the connection prerequisite and clarifies the data scope, including ChatGPT and Copilot-powered search. It does not describe failure behavior when Bing is not connected, but with annotations covering the safety profile that is a minor gap.

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 compact sentences deliver the essential data categories and the prerequisite, with no filler or repetition of the schema. The most informative content is front-loaded.

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 two well-documented parameters, the description covers what data the agent will get and the connectivity precondition. It is complete enough to invoke correctly; the absence of an output schema is offset by the clearly implied payload of queries, pages, metrics, and crawl problems.

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?

The input schema covers both parameters (site and limit) at 100% with detailed descriptions, so the description does not need to repeat them. The description adds no parameter-level meaning beyond what the schema already provides.

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 identifies the resource (Bing performance) and the data returned: clicks/impressions, top queries/pages, and crawl problems, while adding useful context that Bing powers ChatGPT search and Copilot. It distinguishes from likely Google-focused siblings like search_performance through the explicit Bing framing, though it lacks a specific verb such as 'get' or 'list'.

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 prerequisite 'Needs Bing connected in Settings' is explicit and gives actionable context for when the call can succeed. The data categories imply the tool is for Bing-specific SEO performance, but it does not name alternatives or state when not to use it.

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