product_experimentation

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

Annotations already declare readOnlyHint=false, idempotentHint=false, and destructiveHint=true, so the safety profile is present. The description adds scope context about JWT, tenant, and company, but it does not disclose what side effects occur or why the action is marked destructive. It neither contradicts nor enriches the annotations significantly.

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 tightly structured: action, routing, and arguments are presented in three short sections. The core verb and resource appear in the first sentence, and every line carries information without filler.

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?

This is a thin two-parameter wrapper with annotations and an output schema, so the description need not explain return values. It provides the routing and basic argument semantics, but it lacks domain context about what experimentation accomplishes, when to use it, and how it relates to similar product_* or dispatch tools. It is minimally adequate but has clear gaps.

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%, so the description must carry parameter meaning. It does explain that message is a "free-text objective" and inputs is an "optional JSON string of structured inputs," which adds value beyond the raw schema. However, it does not describe what structured inputs are expected, how they map to the experimentation action, or provide any format guidance, leaving meaningful ambiguity.

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 opens with a specific verb and resource: "Run the product domain agent action `experimentation`," which clearly identifies what the tool invokes. However, it does not explain what the experimentation action actually does or differentiate it from sibling tools like product_experiment_design, so it falls short of 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 provides no guidance on when to use this tool versus alternatives. It mentions routing through the platform's domain-agent dispatcher, but that is implementation context, not selection criteria. An agent has no explicit basis for choosing this over dispatch_domain_agent or other product_* tools.

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