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

Annotations only declare read-only, non-destructive, closed-world. The description adds what those annotations cannot: multiple-testing behavior (FDR controlled across every sequence/site pair, with BH vs BY choices described in the schema), that only exact sites are swept while degenerate IUPAC sites are excluded and merely listed, and the statistical meaning of each null. This is meaningful disclosure beyond structured hints.

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?

Purpose is front-loaded in the opening sentence and every subsequent sentence carries information: the biological interpretation, then the three nulls with their rationale. The sentences are long and clause-dense, and the null explanation partially overlaps the enum descriptions, but there is little outright filler.

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 formatting is already covered; all 13 parameters have full schema descriptions; and annotations cover the safety profile. The description adds the conceptual model (nulls, FDR, exact-vs-degenerate handling) an agent needs to call this statistical tool correctly, leaving no meaningful 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 coverage is 100%, so the baseline is 3, but the description goes further by explaining what the null_model alternatives actually mean statistically (order-0 vs k-let preserving vs maximal-order Markov) rather than just restating the enum labels. It does not add much for the other parameters, which the schema already documents.

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 first sentence gives a specific verb (sweep) and resource (every exact recognition site in the NEB catalogue), plus the distinctive output (avoided/enriched sites vs a stated null, with FDR control). That combination is clearly separable from siblings like find_restriction_sites or enzyme_cut_counts, which merely report occurrences without a null model or significance testing.

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 supplies strong context for use — avoidance as evidence of restriction-modification systems, and rarity as a property a design can rely on — and explains why one would pick each null (shuffle keeps dinucleotide skews in the null rather than reporting them as findings; maximal follows published R'MES practice). It stops short of naming a sibling tool or stating explicit when-not conditions, which is the only gap.

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