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

Annotations already declare readOnlyHint/openWorldHint/idempotentHint, and the description layers substantial extra context on top: server-pinned model injection with no override, Claude's autonomous search triggering (max_uses default 5), the full response block structure (server_tool_use, web_search_tool_result, text with citations), and the exact pay-as-you-go billing formula including the no-markup and failed-search-not-billed rules. No contradiction with the readOnly/openWorld annotations.

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?

Purpose is front-loaded in the first sentence, and the text flows logically from mechanism → response format → billing → alternatives. It is long, but every section earns its place given the cost model and multi-block response that need explanation; nothing is filler. Slightly dense, which costs it a perfect score.

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?

Even with a rich output schema and annotations present, the description covers everything an agent needs to call this correctly: billing behavior (including edge case of unbilled failed searches), the non-overridable server-pinned model, the autonomous search trigger count, and the response block layout. Nothing material 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 baseline is 3. The description adds value by linking parameters to behavior — noting messages is 'same format as the Anthropic Messages API' with the user turn holding the question, and explaining that max_tokens is 'required by the upstream Messages API' — contextual rationale the schema lacks. It goes slightly beyond pure schema restatement.

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 specific verb-resource pair ('Ask a question and get an answer that Claude wrote after searching the live web') and explicitly names the two closest siblings it is not — post_tavily_search and post_openai_websearch_search. An agent can distinguish this from a dozen sibling search tools without opening any schema.

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 states the exact use case ('when you want a written, cited answer grounded in current web content') and gives two concrete alternatives with the conditions that select them: open-web research returning ranked links/page text → post_tavily_search, OpenAI-model equivalent → post_openai_websearch_search. This is explicit when/when-not guidance.

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