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

Annotations already establish read-only and open-world behavior, so the bar is lower, and the description still adds meaningful operational context: a per-call cost of $0.002 USDC via x402 on specific chains, the fact that failed calls are not charged, and a hard cap of 10 hits per call. Not disclosed are result ordering, rate limits, or what an empty result means.

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?

One dense paragraph with the resource front-loaded, then returned fields, scope restriction, cap, and pricing in descending order of importance. No filler sentences and nothing repeated.

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?

An output schema exists, so return values need not be explained, and the description still previews them. For a two-parameter read-only lookup, the combination of scope restriction, result cap, and payment terms covers everything an agent needs before invoking it.

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%, with both `gene` (symbol format, length) and `max` (1-10, default 5) fully documented in the schema, so the baseline is 3. The description only restates these ("for a gene symbol", "up to 10 hits per call") plus the useful but minor nuance that the gene must be a mapped symbol.

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 a specific resource (EMBL-EBI GWAS Catalog genome-wide association hits) and the retrieval key (gene symbol), and enumerates the returned data (trait, EFO trait, SNP/locus, p-value, OR/beta, study accession, PubMed ID). That field list makes it clearly distinguishable from variant-level siblings such as health_clinvar_genetic_variants or health_dbSNP_polymorphisms.

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?

"Searches by mapped gene only" is an explicit constraint that tells the agent this tool cannot be used for trait, SNP/rsID or study-level lookups, which is real when-to-use guidance. It stops short of naming an alternative sibling for those other lookup modes, so it is clear context rather than a full routing rule.

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