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

Annotations already cover the safety profile (readOnlyHint, destructiveHint=false, openWorldHint=false), so the bar is lower. The description adds a genuine behavioral trait beyond them: the false discovery rate is controlled 'across every (sequence, site) test', which tells the agent the correction scope spans the whole run rather than per-sequence. It does not disclose cost/runtime implications despite shuffle-based nulls and a 9999 cap on shuffles.

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?

A single front-loaded sentence that opens with the verb and packs scope, output, and statistical control without filler. It is dense but every clause carries information; the lack of a short structure (e.g. splitting method from output) is a minor readability cost only.

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 13 parameters, nested _subject/_files objects, and an output schema already declaring return values, the description supplies enough to identify the tool's purpose and statistical model. It leaves the corpus wiring (sequences vs _subject vs _files vs include_subject) and expected runtime/results size to the schema, which is a reasonable division but not fully complete for such a parameter-heavy tool.

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 is 3. The description's terms ('stated null', 'false discovery rate') map onto null_model and alpha but add no syntax, format, or interaction detail beyond what 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 description names a specific verb and resource ('Sweep a set of sequences against every exact recognition site in the NEB catalog') and states the distinctive output: sites carried far less (avoided) or far more (enriched) often than a null predicts with FDR control. That statistical framing separates it from plain site-locating siblings such as find_restriction_sites or enzyme_cut_counts without needing to name them.

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 sweep-vs-null language signals the statistical-discovery context, but the description never says when to choose this over find_restriction_sites, scan_motif_sites, or enzyme_cut_counts, nor does it state prerequisites like minimum corpus size or which null_model to prefer. The agent must infer the choice from the purpose text.

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