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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds real behavioral context beyond that: the search is 'greedy-plus-steepest-ascent', it runs on 'real measured data', and it makes 'no claim of finding the optimum' — an honest disclosure of the heuristic nature and non-optimal guarantee that an agent would otherwise assume away.

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 purpose before the sibling comparison and the algorithmic caveat. It is dense but every clause carries information; the trailing 'real measured data, a heuristic path, no claim of finding the optimum' is slightly list-like but earns its place as the honesty caveat.

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 optimizer with 8 parameters, a nested subject object, an output schema, and full annotation coverage, the description supplies what the structured fields cannot: the heuristic nature of the search and the explicit alternative tool. Nothing critical is missing for correct invocation, though runtime/determinism nuances are only implied.

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%, so every parameter (including size, fixed, candidate_pool, enzyme, dataset, start_from) is already well documented in the schema. The description reinforces the `fixed` semantics ('junctions you cannot change, such as a destination vector's own overhangs') but adds little else beyond what the schema supplies, so baseline 3 is correct.

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 ('Design a high-fidelity Golden Gate overhang set') plus the scope ('of a given size'). It also names the sibling score_overhang_fidelity and draws the line between them ('that grades a set you already have, this proposes one'), so an agent can distinguish the two without opening any 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?

Explicitly routes the agent: use this when you need to propose a set, use score_overhang_fidelity when you already have one to grade. It also names the 'optionally pinning junctions you cannot change' branch, telling the agent when the fixed-vector case applies. The alternative and its selection condition are stated, not inferred.

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