Ads experiment create

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

Annotations already declare readOnlyHint=false, idempotentHint=false, openWorldHint=true and destructiveHint=false, so the write-path safety profile is covered. The description adds useful lifecycle context (a treatment arm is created in a draft state that must be edited and then scheduled), which explains why the tool is non-idempotent. It says nothing about the `confirm` parameter's role, permission requirements, or what happens if an experiment already exists on the campaign.

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 short sentences, action-and-structure first, follow-up workflow second; nothing redundant. The internal jargon "arm in_design_campaigns" is compact but slightly opaque without prior context.

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?

An output schema exists, so return values need not be described, and annotations cover the mutation safety profile. However, for a 7-parameter mutation with 0% schema description coverage and a `confirm` gate, the description leaves too much for the agent to infer about parameters and preconditions.

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 loosely gestures at traffic split (treatment_traffic_percent) and base_campaign_id ("on a campaign"). It never explains `confirm`, `suffix`, `experiment_type` (default SEARCH_CUSTOM), or `name`, all of which are free-form or defaulted fields an agent must get right.

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 ("Create an A/B experiment on a campaign") plus the structural shape (control + treatment arms, traffic split), which goes beyond the title. It does not explicitly distinguish itself from the adjacent lifecycle siblings ads.experiment.schedule / promote / end, though the closing sentence implies the ordering.

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 real usage context: after creating, edit the treatment draft with ads.mutate, then schedule. That names a sibling tool and a prerequisite step, which is more than most definitions offer. It stops short of stating when NOT to create an experiment or what preconditions (campaign eligibility, existing experiments) apply.

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