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

Annotations already declare readOnlyHint=true and openWorldHint=true, and the description adds real behavioral context beyond that: retrieval happens at run time from an external authority, GO sets use direct annotations only ('NOT annotations dropped'), Reactome sets are restricted to the submitted genes and to the species Reactome resolves, and the output carries source, release and retrieval date. It doesn't mention failure modes or rate limits, but the disclosure is substantial.

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 the purpose, then the two authority branches, then the return value. It is one dense sentence with heavy parentheticals, and the 'NOT annotations dropped' aside is a little cryptic, but nearly every clause carries information an agent needs.

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-value detail needn't be exhaustive, and the description still summarizes the GMT output with provenance. The nested _files/_subject project plumbing is left entirely to the schema, but the core behavior of the tool itself is adequately covered.

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 the schema already documents organism resolution, the reactome-only scope of `genes`, and the authority enum. The description largely restates those semantics (organism resolution path, genes applicability) rather than adding syntax or format guidance, so the baseline of 3 applies.

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 opens with a specific verb+resource ('Gene sets for an organism, fetched from the authority at run time') and immediately names the two concrete sources (GO Consortium annotation file, Reactome AnalysisService). It also names the downstream consumers (gene_set_overrepresentation, gene_set_enrichment, gene_set_camera), which lets an agent place the tool in the workflow rather than guessing.

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?

By stating that the output is GMT text for the three gene_set_* enrichment tools, it makes the when-to-use context explicit: this is the prerequisite fetch step. It does not, however, state any exclusions or say when a bundled-list or lookup_gene/ontology path would be preferable instead.

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