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

Annotations already cover safety (readOnly, openWorld, idempotent, non-destructive), and the description adds genuinely non-obvious behavior: x402 payment of $0.004 USDC on Base or Solana, the required X-PAYMENT header, and a free-trial escape hatch via X-Trial: 1. What it omits is the failure mode when payment is absent (presumably a 402 challenge) and any rate limits, which is why it stops short of 5.

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: the first front-loads the resource and result shape, the second front-loads the payment requirement. No filler, no restatement of the name or 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?

The description compensates well for the missing output schema by enumerating returned fields, and it fully covers the payment prerequisite. But with four undocumented parameters at 0% schema coverage, the unexplained `gl` and the q/query ambiguity leave a real gap for a tool whose only invocation risk is malformed parameters.

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 0%, so the description must carry all parameter meaning, and it only partially does: "one query" and "up to 20" map to query/q and num, but `gl` is never explained (country/language?) and the duplication of `q` and `query` is left unresolved. An agent cannot tell which of the two query fields to populate or what `gl` expects.

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?

"Scholar results ... for one query, up to 20" names a specific verb+resource and enumerates the returned fields (title, url, snippet, publication, year, citations, pdf), which implicitly separates it from web_search/news_search/image_search. It never names a sibling or states the academic-only scope explicitly, so the differentiation is inferential rather than stated.

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 solid invocation guidance for access (send X-PAYMENT, or X-Trial: 1) and a hard cap of 20 results, but it gives no when-to-use/when-not guidance relative to web_search, news_search, or search_extract. An agent knows how to call it but not clearly when to prefer it over the general search siblings.

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