Create A/B Test (Ad Study)

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

Annotations already indicate a mutating, non-idempotent, non-destructive operation, and the description adds the useful detail that it 'Returns: The created study ID'. It does not, however, explain side effects, permissions, or the downstream implications of starting a study, so behavioral disclosure is only average.

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 appropriately sized, front-loaded with the purpose, and organized into a short Args list plus a Returns line. It is not bloated, though some parameter detail duplicates what the input schema already provides.

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?

Most invocation details are covered by the schema and the Args list, but the description does not explain the difference between SPLIT_TEST and HOLDOUT or how cells and treatment percentages should be arranged. With no output schema, the Returns line helps, but key decision semantics remain under-specified.

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 100%, so the baseline applies. The Args list mostly repeats schema field names and descriptions, adding only minor examples like 'act_123456789' and confidence levels 90/95/99, without deeper meaning such as how treatment_percentage values should be distributed across cells.

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 'Creates an A/B test (ad study) to compare campaigns or ad sets', naming a specific verb, resource, and intent. This clearly differentiates it from read-only siblings like meta_get_ad_studies and from general ad-creation tools like meta_create_campaign.

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 first sentence implies when to use it — whenever an A/B test is needed — but there is no explicit guidance about when not to use it or which sibling to prefer, such as meta_get_ad_studies for reading existing studies. No alternatives or exclusions are mentioned.

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