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

With no annotations, the description must carry behavioral disclosure. It states that the tool creates an experiment and returns an object, and explains the causal measurement intent. However, it does not mention side effects, whether the operation is synchronous, permission requirements, or reversibility. 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?

The description is front-loaded with the core purpose, followed by a focused WHEN TO USE section, RETURNS, and a compact EXAMPLE. Every section adds value with no redundancy or 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?

Given the tool's moderate complexity (8 params, no output schema, no annotations), the description covers purpose, usage context, return object, and a full example. It does not mention error conditions or prerequisites (e.g., campaign must exist), but overall it provides sufficient operational context.

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% with descriptive defaults and ranges. The description adds a concrete example showing how campaign_id, experiment_type, treatment_dmas, control_dmas, holdout_pct, and target_mde fit together. This goes beyond the schema and helps the agent construct a valid invocation.

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 opening sentence states a specific action: 'Create an incrementality experiment for a campaign.' It then names the three experiment types (geo-holdout, ghost ads, PSM), clearly distinguishing this from sibling tools like create_campaign and get_incrementality. The verb+resource is specific and unambiguous.

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?

A dedicated 'WHEN TO USE' section lists clear scenarios (setting up A/B test, defining treatment/control DMAs, configuring parameters). It does not explicitly mention when not to use it or name alternative tools, but the context is sufficient to guide selection.

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