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

Annotations only carry readOnlyHint=false and openWorldHint=true; the description does the heavy lifting by disclosing the $0.05 flat cost, the constraint set (basic depth only, ≤5 sources, 400 output tokens), the preflight validation path including AUP fences, and the refund-on-upstream-failure policy. That is exactly the beyond-schema behavioral context an agent needs before spending money.

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, but roughly half the text is payment plumbing (x402, USDC on Solana, _meta key path, HTTP equivalent URL) that is dense and partly irrelevant once an MCP client handles the 402 dance. The HTTP-equivalent sentence in particular is low-value for an MCP caller and could be trimmed.

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 paid, rate/limit-bound tool with no output schema, the description covers cost, caps, failure/refund behavior, and the validation path — enough to call it correctly and predict the charge. The remaining gap is the shape of the returned answer/citations and the lack of positioning against sibling search tools.

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?

One parameter at 0% schema description coverage, so the description must compensate. It does partially: "ask a question" signals natural-language input and "query 3..512 chars" restates the schema's min/max. But the char limits duplicate the schema rather than adding meaning, and it doesn't clarify whether operators, quotes, or URLs are accepted in the query.

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?

Opens with a specific verb+resource+output: "Cited-answer web search: ask a question, get a short synthesized answer with citations to live web sources." That is unmistakably different from a raw crawl or news feed. However, it never names a sibling (wiki_answer, news_search, cse_search) that would be the natural alternative, so differentiation is left to inference.

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 detailed *how-to-invoke* guidance (preflight POST, payment handshake, retry with _meta["x402/payment"]) but no *when-to-use* guidance — nothing says whether to prefer this over wiki_answer or news_search, or what question types it suits. Usage is implied by the price/limit framing rather than stated.

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