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

Annotations declare non-read-only, non-destructive, closed-world, which the description does not contradict; it adds real behavioral context by disclosing the scoring dimensions, that weights drive the penalties, the task:existing branch, and that output feeds a downstream pcr_amplify. It stops short of saying whether results are persisted to the project/notebook, which matters given readOnlyHint=false on what reads like a pure compute tool.

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 core verb and scope, then the task mode, then the downstream consumer and the sibling alternatives. The opening sentence is long and dense, but every clause carries information and nothing is redundant boilerplate.

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 39-parameter designer with an output schema, the description supplies what the schema cannot: the design intent, the task:existing branch, the downstream pcr_amplify handoff, and the sibling routing. Return values need not be explained because an output schema exists.

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 by enumerating the scored penalties (Tm, dimers, hairpins, 3' stability, repeats, clamp, specificity) that correspond to the weight_* arguments, and by framing 'weights you set' as a coherent tuning surface. It does not explain the region/target or conditions parameters beyond what the schema already says.

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 ('ranked search ... scan the open record for primer pairs') and makes the scope explicit (product-size, Tm, length, GC windows; weighted scoring; returns best N). It distinguishes itself from two named siblings, so an agent can route without opening the schema.

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 explicit routing rules: use design_sequencing_primers for a sequencing walk, design_primers for pydna's single-pair designer, and design_primer_pairs for the Primer Designer's own ranked search. It also states the task-mode switch ('With task: existing, supply one primer and it designs the mate').

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