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

Beyond the readOnlyHint/openWorldHint annotations, the description discloses genuinely non-obvious traits: the $0.02 USDC per-call x402 payment, the grounding discipline ("writes only from what they say"), and the model used. That is real added context for a paid, open-world tool. It stops short of describing failure/insufficient-sources behavior or latency.

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 tight sentences, front-loaded with the core value (cited answers from live pages) and then the operational facts (grounding, model, cost). Every clause carries information; no filler or restatement of the title.

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?

With no output schema, the description does the work of describing the return shape (concise answer, numbered citations, source list), which is the critical missing piece. It also covers cost and grounding. Minor gaps remain around edge cases (no results, paywall/blocked pages) and how source count affects behavior.

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 both q and the 2-6 range/default for sources are already documented structurally. The description adds nothing beyond that about parameter meaning or interaction. Baseline 3 is correct when the schema carries the parameter burden.

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 concrete verb+resource: it answers a question with a concise, citation-backed response built from live web pages. The mention of live page reading and numbered [n] citations is specific enough that an agent knows exactly what comes back. It does not, however, name or contrast itself with the obvious siblings (answer_cached, ask, docs_ask), so sibling discrimination 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?

Usage is only implied: an agent can infer this is for a sourced answer to a natural-language question. There is no explicit when-to-use, when-not-to-use, or routing to alternatives such as answer_cached (likely the cheaper repeat path) or docs_ask (for document corpora). The per-call cost hint gestures at cost-sensitivity but does not translate it into selection guidance.

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