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

Annotations already declare readOnlyHint/openWorldHint=false/destructiveHint=false, so safety is covered; the description instead contributes reproducibility behavior — that a seed reproduces upstream p-values exactly and results are bit-identical to enrichit 0.2.6 — plus the statistical machinery (weighted running sum, size-matched permutations, eps floor). It does not mention performance cost or how large ranked lists are handled, so it falls short of a 5.

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 lead noun phrase is well front-loaded, but the first sentence is a single sprawling clause chain, and citations (Subramanian et al. 2005, Korotkevich et al., enrichit 0.2.6, pasilla's DESeq2 Wald statistics) consume significant space without helping an agent invoke the tool. The second sentence is pure validation prose; the valuable output enumeration is buried mid-sentence.

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?

With 14 parameters, full schema coverage, an output schema and safety annotations, the description's burden is modest, and it does cover method provenance, outputs and determinism. What is missing is routing guidance relative to gene_set_overrepresentation and any note on cost/scale for large ranked lists, keeping it short of complete.

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 eps, seed, exponent, min/maxGSSize, scoreType, sampleSize, nPermSimple, pAdjustMethod and the two required inputs. The prose adds essentially no parameter meaning beyond the schema (it restates seeding/eps flooring), which is the baseline-3 case.

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 and resource — preranked GSEA with fgsea multilevel p-values as clusterProfiler's GSEA() runs it — and enumerates the concrete outputs (enrichment score, NES, multilevel p, adjusted p/q, rank at max, leading-edge genes). The word 'preranked' plus the required ranked-statistic input cleanly separates it from the sibling gene_set_overrepresentation, which consumes a plain gene list rather than a ranked statistic vector.

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?

Usage is only implied: the required ranked list of statistics and the GMT gene-set input signal the scenario, but there is no explicit 'use this when you have a full ranked DE result' statement and no exclusions. The sibling gene_set_overrepresentation is never named, so the agent must infer the choice from method terminology alone.

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