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

Goes well beyond the readOnly/idempotent annotations: retracted papers and correction notices are excluded, preprints are included but flagged as not peer reviewed, and the tool explicitly does not judge stance or summarize. It also explains that conclusions are verbatim from abstracts and that results are ordered by evidence level, which is exactly the behavioral context an agent needs.

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 and sources, then behavior. Dense and mostly earns its length, though the stance/no-summary point is restated twice ('judge for yourself whether it supports…' then 'does not judge stance… count a paper as support only when its conclusion says so').

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?

Even though an output schema exists, the description covers sources, ordering, exclusions, preprint flagging, and stance neutrality — everything needed to call this without surprises. Nothing material is missing for a read-only search tool.

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 100%, so baseline is 3, but the description adds real meaning for `query` (use English keywords when the claim is long/non-English) and clarifies the preprint inclusion behavior tied to `include_preprints`. Year and max_results semantics are left to the schema.

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 and resource — find published evidence for and against a claim — and pins down the sources (PubMed, OpenAlex) plus the level-of-evidence ordering. It does not name a sibling (e.g. search_papers) to contrast with, so it stops short of full sibling differentiation.

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 concrete operational guidance: pass `query` in English when the claim is long or non-English, and only count a paper as support/contradiction when its conclusion says so. It never states when NOT to use this tool or which sibling to prefer for plain paper search, so exclusions are absent.

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