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

Annotations only cover the read-only/open-world posture, but the description adds the decisive behavioral fact that this is a paid call ($0.01 USDC via x402 on Base/Solana/Polygon/Arbitrum) with auto-payment for x402 clients and a free sample workaround. It also discloses dedup-by-DOI and field truncation (5 authors, 600-char abstract), which an agent cannot infer from the schema.

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?

Front-loaded with purpose, then returns, then params, then payment, then a sample — a sensible priority order with no filler sentences. The return-field enumeration is slightly long, but justified since there is no output schema.

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 and thin schema descriptions, the description compensates well by describing the returned fields, dedup behavior, payment mechanics, and a sample call. It omits failure/error behavior and any rate limits around the paid x402 flow, leaving a small gap for a tool with this much operational complexity.

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 only 20% (just `year_from`), so the description carries most of the load and does so by restating all five params with required/default/range and enumerating the `source` values. It maps source values to their underlying databases, though `year_from` and `open_access_only` behavior is left largely to their names.

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 specific verb (Search) plus resource (scientific papers) and names the three upstream corpora with scale/domain qualifiers (OpenAlex 250M works, arXiv preprints, PubMed biomedicine). This scope cleanly separates it from general siblings like web_search, news_search, and research_report even without naming them.

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?

Gives clear context (academic paper retrieval, one call across three databases), documents the `source` switch for narrowing to a single corpus, and supplies a concrete example invocation. It stops short of explicit when-not guidance or naming alternatives such as research_report or answer_with_sources for synthesized answers.

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