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

Annotations already declare destructiveHint=false and openWorldHint=true, and the description usefully reinforces this with 'Never deletes' and adds the crucial dry-run behavior ('Previews unless confirm is true') that no annotation conveys. It omits auth/permission requirements and does not address the non-idempotent hint, so it is strong but not exhaustive.

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 tight sentences with the core action, the preview/confirm rule, and the non-destructive guarantee front-loaded in that order. Every clause carries information; no padding.

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 mutation tool with no output schema, the description covers the essential behavioral contract (dry-run default, explicit confirmation, never deletes). The remaining gap is the counting_method parameter, whose enum values and effect are never described anywhere.

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 75% and the confirm parameter is already thoroughly documented in the schema, including the 'set true only after the user has agreed' guidance. The description's event-name examples restate the schema's event_name description rather than adding new meaning, and counting_method's enum is left unexplained in both places.

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 ('Mark an event as a key event (conversion)') scoped to a client's GA4 property, and parenthetically defines what a key event means. The concrete event-name examples make it unmistakable against siblings like ga4_list_key_events or ga4_create_property.

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 clear operative context: preview-by-default with an explicit confirm gate, plus when the tool is relevant ('lead-generation site' with generate_lead/phone_click). It does not name alternatives (e.g. ga4_list_key_events to inspect existing key events first) or state when not to use it, so it stops short of full routing guidance.

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