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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered and the description is not required to restate it. The description does add real conceptual content – results are judged against chance via shuffles rather than tallied – which goes beyond the annotations. It omits notable behavior: the run is computationally heavy (shuffles per record, up to 999), and per-record results are corpus-independent by design, a property buried in the schema's seed text rather than stated up front.

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 sentence with the key distinction front and center and no filler. It is dense to the point of being slightly convoluted – the all-caps 'MORE EXTREME THAN CHANCE' and the trailing 'rather than how many it carries' clause compete for attention – but nothing is wasted.

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?

An output schema exists, so the description need not explain return values, and annotations cover the safety profile. Still, for a 10-parameter statistical sweep with nested subject/file objects and seven available flags (only three of which are named), one sentence leaves the agent without a mental model of what the corpus input should look like or what a 'flag rate' aggregates over. Minimal but not misleading.

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% across all 10 parameters, including rich per-parameter explanations for seed, alpha, shuffles, shuffle_k and correction, so the schema carries the parameter burden. The description adds no parameter-level meaning beyond what is already documented (it does not even mention alpha or the FDR correction). Baseline 3 is appropriate.

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 gives a specific verb and resource ('measure how often a corpus of maps carries...') and draws a sharp line between this tool and plain counting ('MORE EXTREME THAN CHANCE, rather than how many it carries'). The sibling set is full of look-alikes (scan_sigma70_promoters, scan_splice_sites), and while the 'rate vs count' framing implicitly separates it from them, none is named. The term 'maps' for what the schema calls 'sequences' is also slightly loose.

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 implied rather than stated: the agent can infer this is the tool to reach for when it needs significance against a null rather than raw occurrence counts. There is no explicit 'use X when you want counts' routing to scan_sigma70_promoters/scan_splice_sites, and no prerequisites (corpus assembly, cost of many shuffles) are mentioned. Adequate but with clear routing gaps.

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