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

Annotations already declare this as a safe, read-only, non-destructive, non-open-world operation. The description adds rich behavioral context beyond annotations: order-time filtering, deduplication of overlapping targets into one well, per-reason counting of held-back candidates, the headless engine's inability to fetch Rule Set 3 weights, and the deliberate absence of recommended representation/MOI/read depth.

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 purpose is front-loaded in the first sentence, and the description is information-dense rather than repetitive. It is somewhat long and ornate, with clauses like 'every candidate a filter held back is counted by reason' that could be tightened, but each sentence contributes useful scope or behavioral detail.

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?

Given the complex 16-parameter nested schema, full parameter descriptions, annotations, and an output schema, the description provides enough context to call the tool correctly. It covers purpose, filtering behavior, synthesis-ready output, limitations, and what is intentionally not embedded, without needing to explain return values.

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 all 16 parameters in detail, including advanced flags and their defaults. The description adds some framing (best N guides per target, optional barcode, both custom overhangs required) but mostly reiterates what the schema provides, so the baseline of 3 is appropriate.

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 and resource: turning the open record's annotated targets into an ORDERABLE sgRNA oligo pool, with best-N guides per target and synthesis-ready oligo composition. It explicitly distinguishes itself from analysis tools ('It designs a library; it does not analyse one') and from generic guide design by emphasizing orderable pools, cloning overhangs, and subpool barcodes.

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?

Gives clear context for use: designing an orderable sgRNA pool from an open record's annotated targets, and states what it does not do ('does not analyse one'). It also notes that representation, MOI, and read depth are not embedded and points to the editor panel for screen-scale arithmetic. However, it does not explicitly name alternative sibling tools such as crispr_design_guides or when to choose them.

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