cst_optimizer

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

There are no annotations provided, so the description carries the full burden. The description states that a goal is defined with minimize/maximize/target, and parameters vary with bounds. However, it does not disclose important behaviors such as whether the tool modifies the existing project (mutation), requires a running solver, or has side effects (e.g., generating new results). It also doesn't mention that this is a configurational step before running an optimization, which could affect the agent's expectations.

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 a single sentence listing the key components (goal, parameters, algorithm) in a logical order. It is concise and front-loads the core purpose. However, it could be slightly more structured by explicitly listing the parameters or providing an example, but it's efficient and clear.

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?

Given 6 parameters and no output schema, the description covers the main inputs but does not explain the expected output or behavior—such as returning a summary of the optimization setup or actually running the optimization. It also doesn't mention any preconditions (e.g., a project must be open, results must exist for result_path). Since it's a complex tool with nested parameters (parameters array), more context on the workflow would be beneficial.

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?

The schema has 100% description coverage, so parameters like goal_type, result_path, parameters, method, goal_value, max_evaluations are described. The tool description adds a high-level summary but does not add extra meaning beyond what the schema already provides. For example, it doesn't clarify the format of result_path beyond the schema's example, or explain the interaction between goal_type and goal_value beyond the schema's note. Thus, it meets the baseline 3 but does not go beyond.

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 sets up an optimization in CST Studio, with a specific verb ('Set up') and resource ('optimization'). It outlines the main components: goal, parameters, and algorithm. However, it does not explicitly differentiate from sibling tools like cst_parameter_sweep, cst_multi_objective_optimizer, or cst_constrained_optimizer, which might also involve optimization. A brief mention of alternative tools or distinguishing features would elevate it to a 5.

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?

The description implies usage in optimization scenarios, but it does not specify when to use this tool versus alternatives like cst_parameter_sweep (for sweeps) or cst_multi_objective_optimizer (for multi-objective). It also doesn't mention prerequisites like running a simulation first or having results available. The 'result_path' parameter hints at needing existing results, but the description doesn't explicitly state that.

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