Send an A/B push notification

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

Beyond the annotations (readOnlyHint=false), the description explains default behavior (no auto-winner), the intelligent test flow (limited test phase, delay, winner rollout), and a subtle API quirk: 'draft' is conveyed via action query param while body still says status='sent'. This is exactly the kind of behavioral context the rubric values.

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 compact yet dense: every sentence contributes essential behavioral or usage information. It front-loads the core purpose, then layers conditional guidance without redundancy. No filler or repetition.

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 complexity (nested variant objects, multiple optional fields, status handling, audience targeting, intelligent mode), the description covers all critical aspects. Since an output schema exists, return values need not be explained. The description fully prepares an agent to invoke the tool correctly, including edge cases like draft status.

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%, so the baseline is 3. The description adds semantic value by explaining when to set intelligent_ab_test and what happens when omitted, and clarifies the meaning of sent_limit_percentage allocation. While many parameter details are already in the schema, this extra guidance about the interplay between parameters justifies a 4.

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 notification on the current site with two variants', which clearly identifies the tool's action, resource, and scope. It distinguishes itself from the sibling non-A/B tool (pushengage_send_notification) and explicitly names the required variant_a/variant_b parameters.

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 description provides clear when-to-use guidance: how to enable intelligent/auto-winner mode, when to include audience_groups, and which status values to use for scheduling/draft. It also warns against adding unrequested optional fields. However, it does not explicitly name sibling alternatives or state 'use this instead of send_notification when A/B testing is needed', though the name makes this inferable.

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