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

Annotations already establish the safe read-only, closed-world profile, so the description is free to add real substance: the exact redundancy rule (highest percent identity to a row at least as long by ungapped residues), the Jalview gap-matching convention, and the filtering consequence. This is behavior an agent could not infer from annotations or schema.

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 definition leads with the core verb and the redundancy rule, then adds the Jalview caveat and the wiring note. Three compact sentences with no filler, though the middle sentence is dense enough to require a careful read.

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 and 100% schema coverage across six parameters (including nested _files/_subject), the description only needs to carry the algorithm and data-flow. It does both, leaving only minor gaps such as return shape, which the output schema covers.

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 baseline is 3, but the description adds meaning beyond it by explaining that threshold is a percent identity cutoff at or above which a row is redundant and by grounding the comparison span (from/to) in the Jalview shorter-row comparison. The wiring hint for `rows` connects the parameter to a producer tool.

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?

Opens with a specific verb and resource ('Find the rows of an alignment that repeat another') and immediately defines what redundancy means here, so an agent can tell it apart from alignment_agreement or alignment_pca by concept. It stops short of naming a sibling tool it is not, which is what would earn a 5.

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?

Provides a concrete data-flow instruction ('Wire `alignedSequences` from align_sequences') and the downstream intent ('filtering keeps the longest representative of each near-identical group'), which implies when to reach for it. However, there is no explicit when-not guidance or comparison to the other alignment tools in the sibling list.

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