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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered; the description adds genuinely useful behavioral context beyond them: it identifies the exact test and implementation, states that every tested set is bit-identical to enrichit in R, and notes that enrichment requires passing both the p/adjusted-p and q-value cutoffs. It stops short of describing runtime cost or the size limits that drive the min/maxGSSize defaults.

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 method is front-loaded in the first clause and the returned statistics are enumerated compactly, so the key facts land early. The closing sentence about pasilla/Fly GO bit-identity is a trust signal that is more validation than actionable guidance and is the one part that does not fully earn its space.

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 spelled out, and the description still summarises them adequately. Combined with full annotation coverage and 100% schema coverage across 11 parameters, the agent has enough to call the tool correctly; only the lack of routing guidance versus the sibling enrichment tool leaves a gap.

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 every parameter is already documented in the schema, and the description mostly restates schema content (ratios, fold enrichment, cutoffs, background semantics). It adds some framing by tying pvalueCutoff and qvalueCutoff to the notion of 'passing both cutoffs', but no syntax or edge-case guidance beyond the structured fields.

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 names a specific method (one-sided hypergeometric over-representation against a background, clusterProfiler enricher semantics) and the exact family of outputs, so an agent can tell it is an ORA test rather than a GSEA-style scan. It never names or contrasts with the sibling gene_set_enrichment, so the boundary between the two is left for the agent to infer.

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?

Context is implied rather than stated: the genes parameter is described as 'the gene list (e.g. the significant genes of a DE run)' and geneSets as GMT exports, which suggests a post-DE analysis workflow. There is no explicit when-to-use / when-not, no mention of the alternative gene_set_enrichment, and no prerequisites (e.g. ID-type matching is only mentioned inside the geneSets schema field).

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