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

Annotations already state readOnlyHint=true and destructiveHint=false. The description adds meaningful behavioral context: date-range defaults, daily row granularity, ISO 8601 UTC date format, and a specific 404 condition tied to the insights pilot. This goes well beyond the annotations and 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?

Four sentences, each carrying distinct information: what the tool returns, how to get a valid ID, date defaults, metric list and date format, and an edge-case fallback. No filler or redundancy.

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 must explain return values, and it does with a metric list and timestamp format. It also covers prerequisite calls, default ranges, and a likely error path. This is complete enough for an agent to invoke the tool correctly.

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 100%, so the baseline is 3. The description adds value by clarifying date default behavior ('last 7 days when from/to are omitted'), the meaning of row.date, and reinforces the adGroupId prerequisite. This elevates it above baseline, though much parameter detail already lives in the schema.

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?

The description uses a specific verb and resource: 'Get daily performance metrics for a specific ad group (ad set).' It clearly identifies the granularity (ad group vs. campaign) and lists the exact metrics returned, distinguishing this tool from sibling campaign-level or comparative-stat tools.

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?

It explicitly instructs 'Use after nevent_list_paid_ad_groups to get a valid adGroupId' and explains the default date range behavior. It also tells the agent to call nevent_paid_ads_health on a 404. It does not explicitly enumerate when NOT to use it relative to campaign-level insights, but the prerequisite and error-handling guidance are clear.

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