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

Annotations already establish readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuine value beyond that: it clarifies that no refresh is performed and, importantly, that scheduler health is NOT inferred from preferences — a real interpretive caveat that prevents a wrong conclusion from the returned data.

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, no filler, with the read scope front-loaded and the exclusions/caveat following. Every clause 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?

With no output schema, the description does the work of naming the returned fields (preferences, last sync outcome, canonical links) and warning about a common misreading. That is solid for a read-only getter, though it leaves connection_context unexplained.

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% and the single parameter (connection_context, an opaque mctx_v1 token) is undocumented in both schema and description. It is not a complex parameter, so this is a mild gap, but the description adds no meaning about it; baseline 3 is appropriate for a one-param tool where the schema is silent.

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 (read) and enumerates the exact resource set: hourly metrics/asset sync preferences, last sync outcome, canonical workspace links. An agent can distinguish this from sync/mutation siblings like google_ads_accounts_sync or google_ads_management_prepare without opening a schema.

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?

Explicitly bounds the tool's scope: 'No refresh or settings changes,' which tells the agent not to reach for this when it wants to trigger a sync or edit preferences. It stops short of naming a specific alternative tool, but the negative constraint gives clear context for when to use it.

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