run_fault_experiment

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

The annotations already indicate destructive=true, readOnly=false, and idempotent=false, so the safety profile is partially covered. The description adds the scoping detail that all baselines and declared treatments are invoked via the proxy, but it does not disclose side effects, resource consequences, or result behavior beyond that.

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 compact sentence that starts with the main verb and wastes no words. It communicates the core scope efficiently and is easy to parse.

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?

The simple one-parameter call shape and presence of an output schema make basic invocation plausible, but the description omits the prerequisite that a fault experiment must have been planned and that plan_token likely comes from that planning step. For a destructive execution tool, the lack of side-effect or workflow context makes it incomplete.

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 0%, and the description never mentions plan_token. The parameter name and pattern provide some meaning, but the origin of the token, how to obtain it, and its role in selecting baselines or treatments are left entirely implicit.

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 action — running every baseline and declared treatment through the managed loopback proxy — which conveys both the verb and the resource scope. It is distinguishable from the generic sibling run_experiment by its fault-experiment-specific language, though 'declared treatment' and 'loopback proxy' are not further explained.

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?

There is no explicit guidance on when to use this tool versus alternatives such as run_experiment or plan_fault_experiment. The description implies this is the execution phase after experiment planning, but it never states prerequisites, exclusions, or why this tool should be chosen over its siblings.

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