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

Annotations already declare readOnly/openWorld/non-destructive, and the description adds real behavior beyond them: results come from remote authorities at run time (implying fresh, network-dependent output), GO excludes NOT annotations while taking term names from QuickGO, and Reactome restricts output to submitted genes in its own resolved species. It does not mention failure behavior, latency, or what happens if `genes` is supplied with authority=go.

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?

It is a single long sentence packed with nested parentheses, which makes the two-authority distinction hard to parse on a first read. The core purpose is front-loaded, but the structure would be far clearer as two or three short sentences.

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 an output schema present, return-value detail is unnecessary, and the description covers authority choice, organism resolution, and the conditional `genes` parameter. Remaining gaps are minor: no note on failure/latency for remote fetches or on interaction between `genes` and the go authority.

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 already 100%, so the baseline is 3, but the description adds genuine meaning: `organism` is resolved differently per authority (NCBI Taxonomy for GO, Reactome's own resolution) and `genes` is scoped to reactome only. This is useful disambiguation beyond the schema's own text.

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-and-resource: fetching organism gene sets from an external authority at run time rather than a bundled list, and specifies what the two authorities return (GO terms with direct annotations; Reactome pathway members among submitted genes). This clearly separates it from bundled-list siblings such as gene_set_camera, though it never names those siblings explicitly.

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: 'instead of a bundled list' and the authority sub-descriptions hint at when each mode applies, and the `genes` parameter notes it only applies to reactome. There is no explicit statement of when to choose this over gene_set_enrichment, gene_set_overrepresentation, or gene_set_camera, and no prerequisites are given.

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