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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds real behavioral context beyond that: the result includes both directly accessible accounts and, for MCC accounts, their direct client accounts, which tells the agent the result set can be broader than a 1:1 user mapping. It doesn't cover pagination, but an output schema exists to describe returns.

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, front-loaded with what the tool does, then what it returns, then when to call it. No sentence is filler and nothing is buried.

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 zero parameters, an output schema, and full annotation coverage, the remaining burden is workflow positioning and result scope, both of which the description supplies. An agent can decide to call this first and pass the resulting ids onward without further help.

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?

The tool takes zero parameters, so the baseline is 4. The description goes slightly beyond by introducing the customer_id and login_customer_id concepts the agent must carry forward to sibling tools, which is useful setup rather than parameter documentation.

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') plus the scope ('the user can access'). This is clearly distinguishable from siblings like ads_query or ads_audit_campaign, which operate on a single customer rather than enumerating accounts.

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 explicit sequencing guidance ('Call this first') and explains why: downstream Google Ads tools need a customer_id, and manager-reached accounts need login_customer_id. This is exactly the when-and-why an agent needs to order calls correctly.

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