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

Annotations already establish this as a safe read (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the safety burden is lifted. The description usefully adds that mismatches are tolerated and that hits are scored with MIT and CFD, but says nothing about cost, ordering, or the validated flag for bulged hits, which the schema mentions but the description could surface.

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?

One front-loaded sentence that packs purpose, permitted mismatches, and the two scoring metrics without redundant phrases. Minor points lost for the capitalized 'WITHIN' emphasis and the slightly buried parenthetical, but nothing needs trimming.

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 10 parameters, nested _subject/_files objects, and an output schema, the definition needs to convey only intent, which it mostly does. It leaves gaps around the required spacer as the guide, bulge search behavior, and the fact that hitting a cap or a wide search can be costly, so an agent must lean heavily on the schema.

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%, with detailed per-parameter docs including PAM tables and bulge envelopes, so the schema does the heavy lifting and the baseline is 3. The description adds only the framing that mismatches are permitted; it does not clarify spacer length, limit semantics, or nuclease choice beyond what the schema already explains.

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 ('search a sequence for sites a guide could also cut') and adds the scoring outputs (MIT and CFD plus aggregate specificity). The emphasized 'WITHIN that sequence' scopes it to a single sequence, which implicitly distinguishes it from genome-wide work, but it never names the obvious sibling survey_off_targets, so siblings still have to be inferred.

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 states no explicit when-to-use or when-not-to-use conditions and names no alternatives, even though survey_off_targets and screen_guides clearly overlap. The only guidance is the parenthetical scoping hint 'WITHIN that sequence', which is a subtle implication rather than a routing instruction.

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