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

Annotations already cover readOnly, openWorld, idempotent and non-destructive, so the safety profile is done. The description earns real credit on top of that by disclosing the auth/payment model ($0.02 USDC on Base or Solana via X-PAYMENT, or a prepaid Bearer xs_ key) and by admitting the current implementation is extractive rather than generative — a quality caveat an agent should factor in. It omits rate limits, latency/typical runtime, and failure modes (e.g. insufficient credit), which are the remaining behavioral unknowns for a paid call.

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?

Effectively two sentences: the capability first, then the commercial/auth terms. Front-loading the deliverable ahead of the payment details is the right ordering, and nothing is padded. Slightly dense — the payment clause packs currency, chain, header name and an alternative auth scheme into one run-on sentence.

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 conceptually simple retrieval-plus-summarize tool with no output schema, the description should still pin down the return shape (it does: a short answer with numbered citations) and the access requirements (it does: x402 or Bearer key). What is missing is the precondition that a question is actually supplied — required is empty, so an agent could invoke with no q and no query, and nothing warns against that. Mostly complete, with one gap on invocation preconditions.

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 80%, so the baseline is 3 and the schema already documents n (2-6, default 4), gl, and freshness. The description adds no parameter meaning at all and never addresses the q/query alias duplication, which is the one genuinely ambiguous input an agent could get wrong. Adequate but no marginal value.

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 gives a concrete verb chain ("web search, read the top pages, and return a short answer with numbered citations") that clearly separates this tool from raw-retrieval siblings such as web_search, search_extract, and extract. It states the output artifact (a cited answer), so an agent can tell what it gets back without opening the schema. It stops short of naming which sibling to prefer in which situation, which keeps it out of the top tier.

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?

Appropriate usage is only implied: you have a question and want a synthesized, cited answer rather than raw results. The one hard constraint disclosed is commercial rather than conditional — it is paid and explicitly "Not in the free trial," which does help an agent avoid calling it in a free-tier context. There is no explicit when-not guidance or named alternative for long-form research (e.g. deep_research) or raw search.

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