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

Annotations already declare a non-read-only, non-idempotent, non-destructive write. The description adds real behavioral context beyond that: 50/50 split on non-overlapping audiences, statistical winner reporting, and the confirm=false preview mode. It does not cover auth requirements or side effects on the source campaigns, but the added context is meaningful.

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?

Front-loads purpose, then layers in input sourcing, time format, best-practice advice, and preview semantics. Each sentence carries information with no filler, though the middle is dense enough that a reader must parse several distinct facts in one block.

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 complex 9-parameter creation tool, the description covers purpose, key behaviors, preview mode, and time formatting, and an output schema exists so return values need not be explained. Remaining gap is that several parameters (account_id, name, control/treatment names) are undocumented anywhere.

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 carries the full burden, and it only partly does: it explains campaign_a/campaign_b sourcing, the ISO 8601 / unix-seconds format for start_time/end_time, and confirm. account_id, name, control_name, and treatment_name are left undefined, including the meaningful default labels 'A'/'B' for the split.

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 and resource ('Creates a Meta SPLIT TEST (A/B)') plus the scope ('compares two existing campaigns 50/50 on non-overlapping audiences'). This clearly distinguishes it from sibling create tools like create_meta_campaign or create_meta_adset, which create new entities rather than a test over existing ones.

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?

Provides actionable setup guidance: campaign_a/campaign_b should come from list_meta_campaigns, and the two campaigns should differ in ONE variable for a clean read. It also flags the preview path (confirm=false). It stops short of explicitly saying when NOT to use it or naming a formal alternative, so it is clear context rather than full routing.

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