configure_sweep

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

Annotations already provide idempotent/non-destructive signals, and the description adds meaningful behavior: config tracking via config_id, full cross-product semantics, per-value separate runs, and deterministic corner guarantees versus Monte Carlo. It does not cover failure modes or resource implications, but it exceeds the annotation baseline.

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?

The description is front-loaded with the core purpose and then provides dense, useful nuance without filler. Every sentence earns its place, including concrete exclusions and examples.

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?

Despite having no output schema, the description states the key return value (config_id) and lifecycle. Combined with sibling tool run_sweep, the intended flow is clear. It covers use cases, alternatives, and anti-patterns thoroughly.

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% and already documents individual fields, but the description adds crucial semantic guidance: how to set up two-value [low, high] sets for corner analysis, one-part-at-a-time sweeps for sensitivity, and examples like L/W or .lib model swaps. This materially helps an agent construct the parameters array.

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 clearly states the tool configures a multi-parameter sweep for a netlist and returns a config_id for execution. It distinguishes itself from configure_montecarlo and bias-sweep workflows, making its purpose and scope immediately identifiable.

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 explicit when-to-use guidance: corner analysis and sensitivity analysis. It also names the alternative for statistical yield/spread (configure_montecarlo) and explicitly excludes bias sweeps, directing to run_simulation + export_waveform instead.

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