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

Annotations already mark the tool as readOnlyHint=true and idempotentHint=true. The description goes well beyond by stating that scores are predicted, not measured; that models are pre-2016 and superseded; that ordering is a ranking aid only; and that scores are null rather than padded for invalid conditions (SaCas9, Cas12a, SpCas9-NG). This fully discloses the tool's limitations and behavior, adding significant transparency.

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 description is front-loaded with the main purpose in the first sentence. Every subsequent sentence adds value (caveats, validity conditions). While it could be slightly more concise by merging some warnings, the trade-off for clarity is acceptable. No superfluous text.

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?

Despite lacking an output schema, the description explains what the output contains (scored guides), when scores are null, and what the order means. It also handles edge cases (no scan if nuclease omitted). For a tool of this complexity (multiple nucleases, scoring models, validity conditions), the description is remarkably complete without needing to reference external documentation.

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% — all four parameters have descriptions in the JSON schema. The description does not add new parameter-specific details beyond what the schema already provides (e.g., minScore default, nuclease enum, sequence format, searchReverseStrand). According to guidelines, with high schema coverage the baseline is 3, and the description does not improve upon this.

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 explicitly states the tool finds and scores candidate guide RNAs for specific nucleases, which clearly distinguishes it from siblings like crispr_offtarget_check, prime_editing_design, and others. The verb 'Find and score' paired with 'candidate guide RNAs' makes the action and resource unambiguous, and the listed nuclease names differentiate from related CRISPR tools.

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 provides strong usage context: it warns that predictions are not measured, models are superseded, and ordering is only a ranking aid. It also specifies validity conditions (only SpCas9 with NGG PAM and sufficient flanking context; null scores otherwise). However, it does not explicitly name alternative tools (e.g., more accurate models) or say when to prefer those, leaving the agent to infer from the caveats.

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