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

Annotations declare non-destructive, non-idempotent, open-world, write operation; the description adds valuable context beyond annotations: 'Previews unless confirm is true' discloses dry-run behavior, and 'Never unlinks' preempts a plausible destructive concern. It does not describe idempotency or error behavior, which the annotations already partially cover.

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 short sentences with zero waste. Purpose first, prerequisite second, preview/unlink behavior last – front-loaded and easy to parse.

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 4-param write tool with no output schema, the description covers purpose, preconditions, and behavior well. The only gap is the meaning of ads_personalization and the return shape, but those are minor for a link-creation operation.

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 50%. The description explains the confirm/preview semantics but not customer_id, property_id, or ads_personalization. Schema coverage for required params is present, but the optional ads_personalization parameter has no meaning provided anywhere the agent can see.

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 (Link) and two resources (client's Google Ads account, GA4 property), and names the data-flow purpose (key events and audiences flow into Ads). Distinguishes itself from sibling ga4_list_google_ads_links by describing the creation of a link rather than listing existing ones.

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 a clear precondition ('Both must be linked to the same client here') and clarifies the preview/dry-run behavior. Does not explicitly name an alternative tool when the client cannot be matched, but the context is strong enough for correct invocation.

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