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

Annotations only declare the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false); the description's real contribution is the domain fact that the design template is bisulfite-converted DNA, which is genuinely non-obvious. It says nothing about what input record is expected (converted vs genomic), that a design is computed rather than a curated lookup, or what the returned panel contains beyond the existence of an output schema.

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?

One front-loaded sentence with the operative verb and mode first, then the justification. The trailing clause is explanatory rather than redundant, though 'a different template from the one every other designer sees' is slightly rhetorical for the information it carries.

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 25-parameter, nested-object tool that also performs CpG island detection (criteria, island_* params), the description is thin: it does not explain that islands are found first and can be targeted by rank, nor how BSP (CpG-avoiding) and MSP (CpG-covering) designs diverge, both of which are buried in the schema. It is minimally sufficient because the schema and output schema are rich, but it leaves real gaps.

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% and the enum for assay is documented in unusual depth, so the schema does the parameter work. The description adds no parameter-level meaning (no mention of min_non_cpg_c, min_cpg, design_in_island, or the island criteria) beyond restating the assay choice conceptually.

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 names a specific verb and resource ('Design BSP or MSP primers for a methylation assay') and pins the template to CONVERTED strands, which separates it conceptually from the generic designers in the sibling list. It never names an alternative tool (design_primers, design_primer_pairs, design_sequencing_primers) outright, so the differentiation stays implicit rather than operational.

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?

It implies the use case (methylation assays needing BSP or MSP primers) but gives no when-not guidance, no prerequisites about starting from an unconverted genomic record, and no pointer to follow-up tools such as check_methylation_block, check_primer_specificity or primer_check. An agent knows roughly what it is for but must infer the workflow position.

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