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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, so the description is not required to repeat those. Instead it discloses crucial behavioral details: server-pinned model and tool, per-request search cap, output structure with web_search_call and message items, and exact billing formula. This is rich, non-redundant behavioral context that materially affects whether an agent calls the tool and how it interprets results.

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?

Although the description is long, every sentence earns its place. The core purpose and usage guidance are front-loaded, followed by billing and output details. There is no fluff or redundancy; each clause adds value, from the server-controlled cap to the cost formula. It is well-structured and information-dense without being bloated.

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?

The tool is moderately complex (search + model + billing + output structure), but the description covers all critical aspects: how the search is performed, what the output looks like, how billing works, and how it differs from alternatives. An output schema exists, so the description does not need to enumerate every field, but it explains the high-level output shape. For an agent to call this correctly and interpret the response, nothing essential is missing.

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 coverage is 100%, so the description does not need to re-explain each parameter. It adds a minor clarification that `input` can be a message array and that the format matches the OpenAI Responses API, which is useful but not transformative. The baseline of 3 is appropriate; the schema already documents the parameters fully, and the description offers only a small amount of extra context.

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 opens with a clear, specific verb and resource: 'Ask a question and get an answer that an OpenAI model wrote after searching the live web.' It explicitly names two sibling tools and how they differ, so an agent can immediately distinguish it from post_anthropic_websearch_search (Anthropic model) and post_tavily_search (raw links). This exceeds a mere statement of function by providing differentiation.

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?

It gives an explicit when-to-use rule: 'Use this when you want a written, cited answer grounded in current web content from an OpenAI model.' It also names alternatives and directs the agent to them for other use cases. This is exemplary guidance that removes any guesswork about tool selection.

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