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

Annotations only supply the generic safety profile (not read-only, non-destructive, non-idempotent, open-world). The description adds substantive behavioral context annotations cannot express: the one-variant-per-call write model, send_percent splitting of the audience, and that winner selection can be automatic after winner_wait_hours. It does not spell out auth requirements or what the response contains, keeping it short of a 5.

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?

Three tightly packed sentences, front-loaded with the core action before the multi-call mechanic and the winner-selection option. No filler, though the density is high and could be marginally tighter.

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 12-parameter mutation tool with no output schema, the description covers the critical call pattern and the automated vs manual winner path that the schema cannot express. Return-value behavior is undocumented, but with no output schema the burden is lower.

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 is 3. The description goes beyond the schema by explaining how parameters interact across calls (same campaign_id, distinct variant labels) and by clarifying the audience-splitting role of send_percent, which the schema's per-field wording doesn't convey.

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+resource (create one A/B test variant on a campaign) and immediately clarifies the non-obvious cardinality: the API stores a single variant per call. This distinguishes it cleanly from create_campaign, list_ab_tests and select_ab_test_winner.

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?

Gives explicit procedural guidance (call once per variant with the same campaign_id and distinct variant labels; twice for a plain A/B split) and names the alternative path for winner selection ('or use select_ab_test_winner to do it manually'), with the auto_select_winner/winner_wait_hours condition attached.

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