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

Goes well past the readOnly/openWorld annotations: metadata-only with no sequence payload, a hard 10-record cap per call, per-call pricing in USDC via x402 across three chains, and the explicit refund behaviour that failed calls are not charged. Payment/auth mechanics and cost are exactly the kind of context annotations cannot carry.

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?

Three tight sentences, front-loaded with the resource and returned fields, followed by input capability, limits, and cost. No filler and nothing repeated from the schema verbatim.

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?

Output schema exists, so the field list is a bonus rather than a necessity; the description still covers scope, input flexibility, call-size limit, and billing model. Nothing an agent needs before invoking a paid, open-world search is missing.

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% and already documents both params and the 1-10 range, so baseline is 3. The description adds real value on top by giving a concrete accession example (NM_000546) and broadening 'term' to gene names and arbitrary NCBI search expressions, which the schema's character-class description does not convey.

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?

Names the exact database and record type (NCBI GenBank nuccore), then enumerates the returned fields (accession with version, title, length, organism, molecule type, update date) and explicitly rules out sequences. That specificity separates it from neighbouring bio-database siblings such as dbSNP, ClinVar or UniProt without needing to name 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?

Tells the agent what kinds of input are accepted (accession, gene, or any NCBI search term) and the 10-record cap, which implies the search use case. But it never says when to prefer this over dbSNP/ClinVar/PubMed, nor what to do if a term is too broad or returns nothing.

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