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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds value by describing the data sources (NCBI, Ensembl, UniProt), the default fields, and the wildcard behavior, which supplements the annotations. It doesn't contradict them and provides context about what the tool returns without being redundant.

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?

The description is information-dense but well-structured: it opens with the core purpose, then details data sources, return fields, capabilities, and routing to sibling tools. Every sentence adds useful context, and there's no redundant filler. It's longer than minimal but earns its length given the tool's flexibility; only minor trimming would tighten it further.

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?

Given the tool's complexity (multiple query types, wildcards, species filtering, output fields) and that an output schema exists (though not shown here, the description covers the key output fields), the description is complete. It covers all essential aspects: what to search, how to constrain results (size, species, fields), and how to proceed for deeper annotations. No critical information is missing for an agent to use it correctly.

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 100%, so all four parameters are documented in the schema. The description goes beyond by giving concrete examples for the 'q' parameter (e.g., 'BRCA1', 'breast cancer 1', 'GO:0006915') and explaining wildcard usage ('CDK*'), which clarifies the semantics of parameter values. It also lists common species values and the 'all' option, adding practical guidance beyond the schema's minimal descriptions.

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?

The description states a specific verb ('Search') and resource ('the MyGene.info gene database'), enumerates accepted query types (keyword, symbol, name, GO term, etc.), and lists the returned fields. It clearly distinguishes itself from sibling tools by naming the alternatives (mygene.genes.info, mygene.genes.batch) and explaining the difference in scope, so an agent can easily tell them apart.

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 explicitly says 'Use the returned Entrez Gene IDs with mygene.genes.info or mygene.genes.batch for full annotations...' – giving direct guidance on when to use this search tool vs. the follow-up annotation tools. It also notes wildcard support and species filtering, clarifying the tool's applicability for broad searches. This is explicit and actionable.

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