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

Annotations already declare readOnlyHint=true, openWorldHint=false and destructiveHint=false, so safety is covered. The description adds behavioral substance beyond that: it reports both MIT and CFD scoring plus an aggregate, and it explicitly warns the score is sequence-scoped rather than genome-wide. It does not surface pitfalls like the validated:false bulge envelope, but it does not contradict anything.

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 what the tool does and its output, with the scoping constraint placed second. Mostly waste-free, though the self-referential clause 'and it says so rather than inventing one' spends words describing the definition rather than the tool.

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?

A 10-parameter mutation-free search with a full schema, nested objects and an output schema, so return values and argument formats need not be restated. The description supplies the essential missing framing — the search is scoped to the supplied sequence and yields MIT/CFD plus aggregate specificity — leaving little an agent needs that is absent.

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 spacer, subject, nuclease, mismatch/bulge bounds and limit. The description mentions 'allowing mismatches' generically but adds no parameter syntax, ranges or defaults beyond what the schema provides. Baseline 3 is correct here.

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?

Specific verb (search) plus a precise resource (sites a guide could also cut) and an explicit output scope (per-site MIT and CFD scores plus aggregate specificity). An agent can tell this is a within-sequence off-target search, but the description never distinguishes it from the nearby sibling survey_off_targets, which an agent selecting blindly may confuse it with.

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?

The description clearly carves out the applicability domain: 'specificity against what you searched — it is not a genome-wide score.' That is a real when-not signal, but it names no alternative tool for the genome-wide case, so routing between this and survey_off_targets / screen_guides is left to inference.

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