run_fault_experiment

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

Annotations already declare destructive behavior and non-idempotency, so the description doesn't need to repeat that. It adds useful scope (every baseline and treatment) and mechanism (loopback proxy), but it does not explain side effects, state changes, or return behavior. This is adequate but not rich.

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?

A single, direct sentence with no filler. It front-loads the action (Run) and clearly describes the target scope and proxy mechanism, making it highly efficient.

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 the existence of an output schema and annotations, the description lacks essential context: it doesn't explain how plan_id is obtained, what results are returned, or how this tool relates to planning and retrieval siblings. For a destructive operation, more elaboration is warranted.

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 provides no description for plan_id, and the tool description does not compensate. The parameter name is self-explanatory, but there is no detail about where the plan_id originates or any format requirements, leaving the agent to guess.

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 states a clear verb ('Run') and a specific resource ('every baseline and declared treatment') through a named mechanism ('managed loopback proxy'). This distinguishes it from sibling tools like run_experiment and clearly indicates a fault-experiment execution purpose.

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?

No guidance is given on when to use this tool versus alternatives. It does not mention prerequisites like plan_fault_experiment, nor does it state when not to use it. The agent is left to infer the correct usage context.

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