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

Goes well beyond the readOnly/destructive/openWorld annotations by disclosing data provenance ('the result says which numbers came from where'), the preset fallback chain for unpublished values, and the exact findings the check emits (percent of vendor maximum, implied extension time, substitutions per molecule, fraction error-free, each quoting a specification line). This is materially useful pre-call context for a read-only planner. It still doesn't say what happens when a parameter is out of the vendor's window (error vs. warning).

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?

Three sentences, front-loaded with the plan/check split before drilling into provenance and report contents. Dense but each sentence carries distinct information; the em-dash clauses on provenance are slightly heavy for the payload they deliver.

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 12 parameters, nested _subject/_files objects, full schema coverage, annotations and an output schema, the description needs only to frame purpose, provenance and failure reporting — which it does. Minor gap: no statement of what the check does when the reaction exceeds a vendor limit (refuse vs. warn), which an agent planning next steps would want.

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%, so the baseline is 3, but the description adds meaning the schema cannot: it explains that the enzyme value selects a catalogued product whose datasheet supplies the extension rate, while values the manual omits fall back to the Taq or Phusion/Q5 preset. It also constrains anneal_c to a value the agent already obtained from a Tm model rather than a guess.

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?

Names a specific verb and resource ('Plan the cycling programme for an amplicon on a NAMED enzyme') and adds a second, distinct function ('check the reaction against that manufacturer's own published limits'). The dual plan+audit scope is stated outright, which separates it from pcr_amplify (which runs the reaction) and from melting_temperature (which only gives a Tm).

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?

Makes the division of labour explicit: the annealing temperature 'is yours (from design_primers or pcr_amplify)', not something this tool infers, and the enzyme choice selects the datasheet used for extension/denaturation. That tells an agent the prerequisite step before calling. It stops short of naming a competing sibling it should be preferred over or any when-not condition.

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