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

Annotations already declare it a safe read (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the bar is low. The description still adds real behavioral context: it discloses what is actually returned (campaign types, prepare/confirm tool names, deployment gates, asset workflows) and warns that 'availability is not authorization or Google eligibility', which guards against misuse. It omits return shape and any pagination/rate details.

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, no filler, with the discovery scope front-loaded and the caveat held back as a qualifier. Every clause carries information (returned categories, customer scope, non-authorization warning).

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?

There is no output schema, so the description must convey the return surface; it lists the categories of information discoverable but not their structure or shape. Combined with an undocumented connection_context and an unstated call-ordering relationship to the eligibility snapshot, it is adequate but leaves real gaps for an agent deciding how to use the result.

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 50%: customer_id is documented in the schema as a 10-digit id, while connection_context carries only a pattern. The description adds the constraint that the customer must be an 'owned' one, which is meaningful context the schema does not state. Baseline 3 is appropriate given the schema does most of the work.

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 (discover) and enumerates exactly what is returned: implemented campaign types, the exact prepare/confirm tools, deployment gates, and asset workflows for one customer. That scope cleanly separates it from the many google_ads_*_prepare/_confirm siblings, though it never names an alternative outright.

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?

The trailing caveat implicitly contrasts this tool with google_ads_account_eligibility_snapshot ('Availability is not authorization or Google eligibility'), and 'one owned customer' implies a scoping precondition. But there is no explicit statement of when to call this versus the eligibility snapshot or the individual prepare/confirm tools, so usage is only inferable.

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