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

Far beyond the readOnly/idempotent/openWorld annotations, the description discloses that a mismatched reference allele is refused with the bases actually found, that shared allele bases are trimmed to minimal form, that mutagenesis treats all variant classes as one interval replacement, and that indel genotyping returns a named omission with the reason — never an empty list. These behaviors are also consistent with readOnlyHint=true since the tool produces a plan rather than mutating state.

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 every sentence carries operational content: mode selection, isoform-coordinate risk, allele trimming, primer-class coverage, and output refusal behavior. It earns its length for a 13-parameter, two-mode tool, though presenting it as one continuous paragraph slightly reduces scannability compared to a structured breakdown.

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 no output schema, the description carries the burden of defining return behavior and largely succeeds: a consolidated oligo order table, minimal trimmed coordinates, refusal with the bases actually found, and a named omission with a working readout for indels. Remaining gaps — the exact field structure of the order table and network-mode failure behavior — are minor given that the safety profile is already covered by annotations.

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% and each parameter description is already rich (bounds, refusal conditions, mode tagging, even a quoted error message). The main description adds the cross-parameter semantics the schema cannot express alone: that KASP requires a single-base substitution's 3'-terminal base, linking the ref/alt inputs to the shape of the genotyping output, and tying the trimming behavior to how anchored VCF pairs are interpreted.

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 a specific verb+resource: 'Turn one variant into one buildable plan' and enumerates the complete pipeline — verifying the reference allele, applying the edit, designing site-directed mutagenesis primers, designing KASP/ARMS genotyping primers, and consolidating into a single oligo order table. This clearly distinguishes it from sibling tools like site_directed_mutagenesis or kasp_primer_design, which cover only one stage of that pipeline.

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 delimits the two mutually exclusive input modes (offline sequence+position vs network HGVS resolved through MANE/Ensembl) and the refusal/omission conditions that govern when results come back. It does not explicitly name sibling alternatives or state 'use X instead when you only need one stage,' but the consolidated 'bridge' purpose makes the scope reasonably inferable from context.

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