draft_key_event

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

Description discloses that it returns a preview (not final), requires calling confirm_and_apply with plan_id to execute, and applies only to future data. Annotations have readOnlyHint=false and destructiveHint=false, so no contradiction, but description adds critical workflow context.

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 sentences with no fluff. Front-loads purpose, then usage, then next steps. Every sentence earns its place.

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 returns a preview and has an output schema, the description explains the workflow (draft then confirm_and_apply). It covers the lifecycle and data effect (future only). Sufficient for an agent to use correctly.

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 0%, so description must explain parameters. It explains counting_method with examples (ONCE_PER_EVENT for purchases, ONCE_PER_SESSION for sign-ups). Event_name is implied by context, property_id is not explained. Partially compensates for schema gap.

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 clearly states the tool drafts a GA4 event as a key event (conversion) and returns a preview. It distinguishes from siblings like attribution_check and validate_tracking by saying it 'closes the loop'.

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 context for when to use: after diagnosis by attribution_check/validate_tracking. Gives examples for counting_method choices (purchases vs sign-ups). Implicitly says not to use before diagnosis.

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