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

Annotations already cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true), so the bar is lower. The description adds real behavioral context beyond them: the BETA marker, the 'no effect until assigned to a campaign' semantics, the 30-day attribution window, and the custom_event_name format constraint. It does not mention permissions, duplicate-handling, or failure modes.

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-loaded with the beta warning and the core action, then a compact enumeration of parameter rules — no filler. It is one dense block rather than separated lines, which makes scanning slightly harder, but every sentence carries 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?

An output schema exists, so return values need no explanation, and the description still supplies the workflow preconditions, event-type vocabulary, and custom-event constraints an agent needs. The only gap is the undescribed required 'name' parameter, which leaves a small ambiguity about what that label should contain.

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 must compensate — and it largely does: full enumeration of valid event_type values, the rule that custom_event_name applies only when event_type=custom (with charset restrictions), the provenance of source_id, and that workspace is optional with a single workspace. Only the required 'name' parameter is left entirely undefined.

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?

Specific verb+resource: create a conversion event (setting) in the OpenAI Ads account and states exactly what it defines — which pixel events count as conversions, with a 30-day click attribution window. It is clearly distinguishable from sibling tools like openai_ads_create_pixel, openai_ads_conversion_setup, and openai_ads_upload_conversions because it names the object being created and its role in the conversion chain.

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 the critical operational context: the setting only counts once assigned to a campaign via openai_ads_update_campaign (add_conversion_event_setting_ids), and source_id must come from openai_ads_conversion_setup (pixels[].source_id). That routes the agent correctly through a multi-step workflow, though it never states when NOT to create one (e.g. duplicate settings, choosing an existing one instead).

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