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

Annotations already mark readOnlyHint=true and idempotentHint=true, and the description adds rich behavioral detail consistent with those hints: detailed coordinate conventions ('1-based inclusive'), the fact that the PAM search runs on the unedited sequence, the dual-flap annealing mechanism, and the explicit limitation 'Off-target activity is not evaluated.' This goes well beyond the structured annotations and helps the agent set expectations for outputs and algorithm behavior.

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 dense but each sentence carries load-bearing information: biological mechanism, coordinate rules, and limitations. It is front-loaded with the primary purpose, then explains the mechanism and constraints. Some sentences are long and technical, which is acceptable given the complexity of a dual pegRNA design tool, but the density reduces readability slightly.

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?

For a complex tool with six parameters and no output schema, the description covers the necessary context: when to use it, what the algorithm does mechanically, how coordinates are defined, what returned fields mean, and what limitations exist (no off-target scoring). It also accounts for edge cases like pure insertions via replaceEnd = replaceStart - 1, which the schema mentions but the description reinforces the intended context.

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?

The input schema already documents all six parameters with 100% coverage, so the baseline is 3. The description adds meaningful coordinate semantics (protospacerStart/protospacerEnd/nickPosition are 1-based inclusive in the PRE-EDIT target frame) and clarifies that replaceSpan refers to the 'span of the new content in the returned editedSequence,' which assists in interpreting replaceStart/replaceEnd and newSequence. This supplements—rather than merely repeats—the schema's per-parameter descriptions.

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 opens with 'Design a twinPE pegRNA pair' — a specific verb plus resource — and immediately distinguishes it from single pegRNA design by noting it's for a replacement 'too large for a single pegRNA's RTT.' It also contrasts the mechanism with 'without an HDR donor,' which differentiates it from similar CRISPR design siblings like crispr_hdr_donor or prime_editing_design.

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?

Clear use condition is stated: use when a replacement is too large for a single pegRNA's RTT. The description does not explicitly name sibling alternatives or state 'do not use if X', but the context is sufficient to infer this tool is the twinPE-specific counterpart to prime_editing_design. The absence of off-target evaluation also provides a boundary on expected behavior.

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