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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description goes beyond that by disclosing the statistical behavior: FDR is controlled 'across every (sequence, site) test,' and the three nulls are explained, including what each does and does not treat as signal (e.g. uShuffle holding CpG depletion in the null). It omits compute cost/runtime characteristics, keeping it out of the top band.

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 core action is front-loaded in the first sentence with the enrichment/avoidance outcome and the FDR guarantee. The remaining sentences are dense but each carries information; it runs long and would benefit from breaking the null-model discussion out, so it is not maximally tight.

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, the description need not explain return values, and annotations carry the safety profile. It covers purpose, statistical meaning, and the three null models, which is enough for correct invocation; the main gap is the absence of explicit when-to-use routing against restriction-site siblings.

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 baseline would be 3. The description adds genuine meaning on top, elaborating the null_model choices (order-0 Poisson, uShuffle k-let shuffles, R'MES maximal-order Markov judging a length-k site against the record's own (k−1)-mers) far beyond the enum labels, which is the semantically dominant parameter.

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?

States a specific verb and resource with precise scope: 'Sweep a set of sequences against every exact recognition site in the NEB catalog and report the sites each one carries far less (avoided) or far more (enriched) often than a stated null predicts.' The statistical framing (FDR-controlled avoidance/enrichment) clearly separates it from simple finders like find_restriction_sites or enzyme_cut_counts, so an agent can tell what it does without opening the schema.

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?

It gives motivating context ('Avoidance is evidence of the restriction–modification systems a lineage has lived with, and a site a design can rely on being rare') but never states when to choose this over alternatives or any exclusions. Usage is implied by the biological framing rather than spelled out, and no sibling is named as an alternative.

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