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

Annotations already declare a safe, read-only, closed-world computation, so the bar is lower. The description adds real behavioral context beyond that: it emits both soft- and hard-masked sequences plus masked intervals, and notes that WindowMasker thresholds are derived from the context SET rather than organism-wide.

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?

Two sentences, front-loaded with the core action and immediately followed by the masker taxonomy and the output rationale. Dense and mostly waste-free, though the long enumerations make it heavier than strictly necessary.

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 a full output schema covering return values and annotations covering the safety profile, the description supplies the missing motivation and masker-selection logic. It could go further by tying itself explicitly to the search/alignment siblings it is meant to precede, but nothing an agent needs to invoke it correctly is missing.

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 schema already documents every parameter, including the masker-specific applicability of hicut, locut, level, window, unit_size and context. The description reinforces the DNA/protein split but adds no new syntax or defaults, so the baseline 3 applies.

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 (mask) plus the exact resource and scope: the regions a similarity search should not seed on. It names and differentiates all three maskers (DUST, SEG, WindowMasker) with what each targets, so an agent can act 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?

Clearly frames when this belongs in a pipeline (mask before searching rather than explaining an empty hit table afterwards) and which masker suits which substrate (DNA vs protein). It stops short of naming the search sibling it should precede or stating exclusions, so it is clear context without explicit alternatives.

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