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

Annotations establish this is a write operation (readOnlyHint=false) with no destructive semantics, so the description's job is to add context. It does: equal audience split per cell, tested objects retain their own budgets, and the test does not auto-activate the objects — they must be activated separately. What is missing is any note on permissions, whether the test can be edited/deleted later, or what identifies the created test.

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?

Two tightly packed sentences, front-loaded with the core action and its cardinality limit, with no redundant or filler wording. Every clause adds operational information.

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?

For a 9-parameter mutation tool with no output schema, the description covers the domain semantics well but omits the metadata parameters (name, description, folder, account, language) and says nothing about what is returned (e.g., a test ID or URL). An agent would know what the tool does conceptually but still guess at several inputs.

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 only 33%, so the description must compensate. It clarifies ids_or_names (2-5 existing campaigns/ad sets, equal audience share) and end_date/start_date (a date range), but name, description, folder, and account are unexplained in both description and schema, leaving four of nine parameters opaque.

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?

States a specific verb (Create) plus resource (split test between existing campaigns or ad sets), with the 2-5 cell constraint spelled out. It implicitly distinguishes itself from the sibling meta_ab_tests (which lists tests) by requiring pre-existing objects, but never names that sibling or meta_create_campaign as the alternative path.

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 phrase 'existing campaigns or ad sets' implies a prerequisite that the tested objects must already exist, which is useful context. However, there is no explicit when-to-use versus when-not guidance, no mention of how this differs from simply creating a new campaign, and no pointer to meta_ab_tests for reviewing results afterward.

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