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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds genuinely non-obvious cross-tool behavior — that downstream tools self-select when only one account is reachable — which is not derivable from annotations or schema.

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 sentences, front-loaded with the action and result, followed by the exact downstream usage. No filler or restatement of the title.

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 usefully signals that the return value is a set of customer ids, and it explains when the tool must actually be called. Minor gap: it does not state what happens on zero reachable accounts, but that is a small omission for a zero-param list tool.

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?

This tool takes zero parameters, so the baseline is 4. The mention of customerId adds useful framing about how the output feeds other tools, though it is not a parameter of this tool.

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 — 'List the Google Ads accounts (customer ids) this connection can access' — and clarifies the return type as customer ids. It is trivially distinguishable from siblings like get_account_summaries or create_google_ads_link.

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 tells the agent what to do with the result ('Pass one as customerId for the other tools') and the condition under which it matters ('only required when more than one account is reachable'). It also pre-empts a needless call by explaining that other tools auto-pick a single account.

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