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

Annotations already declare this a read-only, non-destructive, closed-world operation, so the bar is lower. The description still adds real value by defining the output semantics precisely (INDEL frequency in percent) and pinning the model to wild-type SpCas9, which tells the agent the score is not transferable to other Cas variants. It does not discuss scoring scale interpretation or limits, which the output schema partly covers.

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?

A single sentence front-loads the action, names the model, gives the citation for provenance, and defines the return value with no filler. Nothing could be removed without losing information.

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 fully described input schema and a present output schema, the description only needs to convey what the model is and what the number means, which it does. The remaining gap is guidance on the score's scale/interpretation and its relation to sibling scoring tools.

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%, including a detailed note on the exact 30-nt context layout and null-scoring behavior for invalid input. The description adds no parameter-level meaning beyond that, 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 ('Score'), resource ('CRISPR guides'), and the exact model used (DeepSpCas9, cited to Kim et al. 2019), plus what the returned number means (predicted INDEL frequency in percent). It does not explicitly name the sibling crispr_score_deephf, so the agent must infer the distinction from 'wild-type SpCas9' rather than being told.

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?

Usage is only implied: score guide contexts with the DeepSpCas9 model. There is no explicit statement of when to prefer this over crispr_score_deephf, crispr_design_guides, or screen_guides, and no prerequisites or exclusions are given. The 'wild-type SpCas9' qualifier is the only implicit routing signal.

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