cst_refine_antenna

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

With no annotations, the description carries the full burden and does well: it discloses the per-iteration sequence (set params, run solver, export S11, evaluate), the silent VBA mode that avoids history bloat, the permanent application of best parameters at the end (an important irreversible side effect), and the live-session requirement. It stops short of runtime/cost expectations or what happens on failure or max-iteration exhaustion.

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?

Four tight sentences, front-loaded with the core action and ending with the critical precondition. No filler; slightly fragmented structure as it interleaves mechanism and constraints.

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?

No output schema exists and no annotations are present, so the description must cover behavior — which it largely does (loop mechanics, mutation at the end, session requirement). It omits what the call returns (best parameters, achieved VSWR, convergence status) and expected duration, which an agent scheduling a long optimization 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 description coverage is 100%, so the schema already documents port, bands, parameters, and max_iterations. The description adds only indirect meaning ('VSWR goals across specified frequency bands') and gives no guidance on how the Nelder-Mead search interacts with min/max bounds or how many iterations are typically needed.

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: run a Nelder-Mead optimization loop tuning CST design parameters toward VSWR goals across frequency bands. That distinguishes it in spirit from cst_optimizer / cst_multi_objective_optimizer / cst_parameter_sweep, but no sibling is named, so the agent must infer the boundary itself.

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 gives a real precondition ('Connected mode only: requires a live CST session with a solvable project'), which is useful context for selecting it. However, it never says when to prefer this over cst_optimizer or cst_multi_objective_optimizer, nor when not to use it (e.g. many parameters, multi-objective goals).

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